{"generatedAt":"2026-09-06T13:25:29Z","counts":{"total":197,"available":23,"availableNow":23,"notAvailable":174,"matched":123,"newest":53},"sourcing":"The catalog is a union of two clearly tagged sets. AVAILABLE models come from the gateway's own /v1/models endpoint — they are served and callable today. NOT-AVAILABLE models are a curated set of other notable models shown for feature comparison only; they are not callable via your key. Detail (pricing, context, modality, description) is enriched by best-effort id matching against a public model index.","models":[{"id":"vidu/viduq2","displayName":"Vidu Q2","provider":"Vidu","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":2,"knowledgeCutoff":null,"shortDescription":"Vidu Q2 video generation — previous generation. Flat US$2.00 per clip. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"vidu/viduq3-turbo","displayName":"Vidu Q3 Turbo","provider":"Vidu","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":2,"knowledgeCutoff":null,"shortDescription":"Vidu Q3 Turbo video generation — faster turnaround. Flat US$2.00 per clip. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"vidu/viduq3-pro","displayName":"Vidu Q3 Pro","provider":"Vidu","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":2,"knowledgeCutoff":null,"shortDescription":"Vidu Q3 Pro video generation — high quality. Flat US$2.00 per clip. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-3.0-omni-720p-ref-audio","displayName":"Kling 3.0 Omni (720p, reference, audio)","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":2.2,"knowledgeCutoff":null,"shortDescription":"Kling 3.0 Omni (720p, reference, audio) video generation — reference image with audio. Flat US$2.20 per clip. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-3.0-omni-720p-ref-mute","displayName":"Kling 3.0 Omni (720p, reference, silent)","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1.6,"knowledgeCutoff":null,"shortDescription":"Kling 3.0 Omni (720p, reference, silent) video generation — reference image, no audio. Flat US$1.60 per clip. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"bytedance/doubao-seedance-2-0-260128","displayName":"Seedance 2.0","provider":"ByteDance","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":11.11,"knowledgeCutoff":null,"shortDescription":"Seedance 2.0 — ByteDance's latest video generation. Billed by clip length: US$11.11 for a 5s 720p clip (1–12s supported). Submit via POST /v1/videos with `duration`, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"bytedance/doubao-seedance-2-0-fast-260128","displayName":"Seedance 2.0 Fast","provider":"ByteDance","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":8.06,"knowledgeCutoff":null,"shortDescription":"Seedance 2.0 Fast — ByteDance's latest video generation. Billed by clip length: US$8.06 for a 5s 720p clip (1–12s supported). Submit via POST /v1/videos with `duration`, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"bytedance/doubao-seedance-2-0-mini","displayName":"Seedance 2.0 Mini","provider":"ByteDance","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":5.01,"knowledgeCutoff":null,"shortDescription":"Seedance 2.0 Mini — ByteDance's latest video generation. Billed by clip length: US$5.01 for a 5s 720p clip (1–12s supported). Submit via POST /v1/videos with `duration`, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/veo-3-1-fast","displayName":"Veo 3.1 Fast","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1,"knowledgeCutoff":null,"shortDescription":"Veo 3.1 Fast video generation — faster turnaround. Flat US$1.00 per clip, typically ready in ~161s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/veo-3-1","displayName":"Veo 3.1","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1.6,"knowledgeCutoff":null,"shortDescription":"Veo 3.1 video generation — flagship quality. Flat US$1.60 per clip, typically ready in ~98s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"pixverse/pixverse-c1-720p-audio","displayName":"PixVerse C1 (720p, audio)","provider":"PixVerse","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.77,"knowledgeCutoff":null,"shortDescription":"PixVerse C1 (720p, audio) video generation — 720p with audio. Flat US$0.77 per clip, typically ready in ~65s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"pixverse/pixverse-v6-1080p-audio","displayName":"PixVerse V6 (1080p, audio)","provider":"PixVerse","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1.35,"knowledgeCutoff":null,"shortDescription":"PixVerse V6 (1080p, audio) video generation — 1080p with audio. Flat US$1.35 per clip, typically ready in ~80s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"pixverse/pixverse-v6-720p-audio","displayName":"PixVerse V6 (720p, audio)","provider":"PixVerse","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.71,"knowledgeCutoff":null,"shortDescription":"PixVerse V6 (720p, audio) video generation — 720p with audio. Flat US$0.71 per clip, typically ready in ~69s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-3.0-omni-720p-noref-audio","displayName":"Kling 3.0 Omni (720p, audio)","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1.6,"knowledgeCutoff":null,"shortDescription":"Kling 3.0 Omni (720p, audio) video generation — 720p with audio. Flat US$1.60 per clip, typically ready in ~113s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-3.0-omni-720p-noref-mute","displayName":"Kling 3.0 Omni (720p, silent)","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1.2,"knowledgeCutoff":null,"shortDescription":"Kling 3.0 Omni (720p, silent) video generation — 720p, no audio. Flat US$1.20 per clip, typically ready in ~66s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-3.0-omni","displayName":"Kling 3.0 Omni","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":2,"knowledgeCutoff":null,"shortDescription":"Kling 3.0 Omni video generation — flagship, audio + reference. Flat US$2.00 per clip, typically ready in ~80s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"xai/grok-1.5-video-6s","displayName":"Grok 1.5 Video (6s)","provider":"xAI","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.8,"knowledgeCutoff":null,"shortDescription":"Grok 1.5 Video (6s) video generation — 6s clip. Flat US$0.80 per clip, typically ready in ~50s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"xai/grok-video-3-10s","displayName":"Grok Video 3 (10s)","provider":"xAI","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.8,"knowledgeCutoff":null,"shortDescription":"Grok Video 3 (10s) video generation — 10s clip. Flat US$0.80 per clip, typically ready in ~66s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"xai/grok-video-3","displayName":"Grok Video 3","provider":"xAI","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.8,"knowledgeCutoff":null,"shortDescription":"Grok Video 3 video generation — 5s clip. Flat US$0.80 per clip, typically ready in ~48s. Submit via POST /v1/videos, poll GET /v1/videos/{task_id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"bytedance/doubao-seedance-1-5-pro_1080p","displayName":"Seedance 1.5 Pro (1080p)","provider":"ByteDance","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1.56,"knowledgeCutoff":null,"shortDescription":"Seedance video generation — text-to-video and image-to-video. Flat US$1.56 per generation (5s 1080p clip). Submit via POST /v1/videos with a `seconds` parameter (not `duration`), poll GET /v1/videos/{id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"bytedance/doubao-seedance-1-5-pro_720p","displayName":"Seedance 1.5 Pro (720p)","provider":"ByteDance","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.7,"knowledgeCutoff":null,"shortDescription":"Seedance video generation — text-to-video and image-to-video. Flat US$0.70 per generation (5s 720p clip). Submit via POST /v1/videos with a `seconds` parameter (not `duration`), poll GET /v1/videos/{id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"bytedance/doubao-seedance-1-5-pro_480p","displayName":"Seedance 1.5 Pro (480p)","provider":"ByteDance","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.32,"knowledgeCutoff":null,"shortDescription":"Seedance video generation — text-to-video and image-to-video. Flat US$0.32 per generation (5s 480p clip). Submit via POST /v1/videos with a `seconds` parameter (not `duration`), poll GET /v1/videos/{id}.","createdISO":"2026-08-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-08","openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-2.5-1080p","displayName":"Kling 2.5 (1080p)","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1,"knowledgeCutoff":null,"shortDescription":"Kling video generation — text-to-video and image-to-video. Flat US$1.00 per generation (5s 1080p clip per call). Submit via POST /v1/videos, poll GET /v1/videos/{id}.","createdISO":"2026-07-31","matched":false,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-2.5","displayName":"Kling 2.5","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":1,"knowledgeCutoff":null,"shortDescription":"Kling video generation — text-to-video and image-to-video. Flat US$1.00 per generation (5s clip per call). Submit via POST /v1/videos, poll GET /v1/videos/{id}.","createdISO":"2026-07-31","matched":false,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"kwai/kling-2.5-720p","displayName":"Kling 2.5 (720p)","provider":"Kuaishou","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":null,"inputPricePerM":0,"outputPricePerM":0,"requestPricePerCall":0.6,"knowledgeCutoff":null,"shortDescription":"Kling video generation — text-to-video and image-to-video. Flat US$0.60 per generation (5s 720p clip per call). Submit via POST /v1/videos, poll GET /v1/videos/{id}.","createdISO":"2026-07-31","matched":false,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"anthropic/claude-opus-5","displayName":"Claude Opus 5","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":5,"outputPricePerM":25,"knowledgeCutoff":null,"shortDescription":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review a…","createdISO":"2026-07-24","matched":true,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-08-05","openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"benchIntelligence":60.7,"benchCoding":78,"benchAgentic":55.3,"unavailableReason":"no enabled provider key serves it"},{"id":"moonshotai/kimi-k3","displayName":"Kimi K3","provider":"Moonshot AI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":3,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is…","createdISO":"2026-07-16","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":true,"sourceUrl":"https://huggingface.co/moonshotai","maxOutputTokens":null,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":57.1,"benchCoding":76.2,"benchAgentic":50.1},{"id":"google/gemini-3-pro-image","displayName":"Nano Banana Pro (Gemini 3 Pro Image)","provider":"Google","modalityIn":["image","text"],"modalityOut":["image","text"],"contextLength":65536,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal…","createdISO":"2026-06-18","matched":true,"available":true,"availableNow":true,"newest":true,"openSource":false,"maxOutputTokens":32768,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3.1-flash-image","displayName":"Nano Banana 2 (Gemini 3.1 Flash Image)","provider":"Google","modalityIn":["image","text"],"modalityOut":["image","text"],"contextLength":131072,"inputPricePerM":0.5,"outputPricePerM":3,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It…","createdISO":"2026-06-18","matched":true,"available":true,"availableNow":true,"newest":true,"openSource":false,"maxOutputTokens":32768,"tokenizer":"Gemini","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"anthropic/claude-fable-5","displayName":"Claude Fable 5","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":10,"outputPricePerM":50,"knowledgeCutoff":null,"shortDescription":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning…","createdISO":"2026-06-09","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"benchIntelligence":59.9,"benchCoding":76.5,"benchAgentic":52.8,"unavailableReason":"no enabled provider key serves it"},{"id":"anthropic/claude-opus-4-8","displayName":"Claude Opus 4.8","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":5,"outputPricePerM":25,"knowledgeCutoff":null,"shortDescription":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a…","createdISO":"2026-05-27","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","verbosity"],"benchIntelligence":55.7,"benchCoding":74.3,"benchAgentic":47.2,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-3.5-flash","displayName":"Gemini 3.5 Flash","provider":"Google","modalityIn":["text","image","video","file","audio"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":1.5,"outputPricePerM":9,"knowledgeCutoff":"2025-01-01","shortDescription":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding…","createdISO":"2026-05-19","matched":true,"available":true,"availableNow":true,"newest":true,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":50.2,"benchCoding":70.1,"benchAgentic":37.4,"unavailableReason":null},{"id":"google/gemini-3.1-flash-lite","displayName":"Gemini 3.1 Flash Lite","provider":"Google","modalityIn":["text","image","video","file","audio"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.25,"outputPricePerM":1.5,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and…","createdISO":"2026-05-07","matched":true,"available":true,"availableNow":true,"newest":true,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/antigravity-preview-05-2026","displayName":"Antigravity Preview 05 2026","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Antigravity Preview 05 2026 is served live on the gateway today (input: text).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-flash-latest","displayName":"Google Gemini Flash Latest","provider":"Google","modalityIn":["text","image","video","file","audio"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":1.5,"outputPricePerM":9,"knowledgeCutoff":"2025-01-01","shortDescription":"This model always redirects to the latest model in the Google Gemini Flash family.","createdISO":"2026-04-27","matched":true,"available":true,"availableNow":true,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-pro-latest","displayName":"Google Gemini Pro Latest","provider":"Google","modalityIn":["audio","file","image","text","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"This model always redirects to the latest model in the Google Gemini Pro family.","createdISO":"2026-04-27","matched":true,"available":true,"availableNow":true,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"anthropic/claude-opus-4-7","displayName":"Claude Opus 4.7","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":5,"outputPricePerM":25,"knowledgeCutoff":null,"shortDescription":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers…","createdISO":"2026-04-16","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"benchIntelligence":53.5,"benchCoding":73.6,"benchAgentic":44.4,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemma-4-26b-a4b-it","displayName":"Gemma 4 26B A4B  (free)","provider":"Google","modalityIn":["image","text","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference —…","createdISO":"2026-04-03","matched":true,"available":true,"availableNow":true,"newest":true,"sourceUrl":"https://huggingface.co/google","openSource":true,"maxOutputTokens":16384,"tokenizer":"Gemma","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":25.7,"benchCoding":39.3,"benchAgentic":11,"unavailableReason":null},{"id":"google/gemma-4-31b-it","displayName":"Gemma 4 31B (free)","provider":"Google","modalityIn":["image","text","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable…","createdISO":"2026-04-02","matched":true,"available":true,"availableNow":true,"newest":true,"sourceUrl":"https://huggingface.co/google","openSource":true,"maxOutputTokens":262144,"tokenizer":"Gemma","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"benchIntelligence":29.4,"benchCoding":43.4,"benchAgentic":14.4,"unavailableReason":null},{"id":"google/deep-research-max-preview-04-2026","displayName":"Deep Research Max Preview 04 2026","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Deep Research Max Preview 04 2026 is served live on the gateway today (input: text).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/deep-research-preview-04-2026","displayName":"Deep Research Preview 04 2026","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Deep Research Preview 04 2026 is served live on the gateway today (input: text).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/lyria-3-clip-preview","displayName":"Lyria 3 Clip Preview","provider":"Google","modalityIn":["text","image"],"modalityOut":["text","audio"],"contextLength":1048576,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...","createdISO":"2026-03-30","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Other","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["max_tokens","response_format","seed","temperature","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/lyria-3-pro-preview","displayName":"Lyria 3 Pro Preview","provider":"Google","modalityIn":["text","image"],"modalityOut":["text","audio"],"contextLength":1048576,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate…","createdISO":"2026-03-30","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Other","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["max_tokens","response_format","seed","temperature","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-3.1-flash-lite-preview","displayName":"Gemini 3.1 Flash Lite Preview","provider":"Google","modalityIn":["text","image","video","file","audio"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.25,"outputPricePerM":1.5,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini…","createdISO":"2026-03-03","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":25,"benchCoding":34.7,"benchAgentic":6.2,"unavailableReason":null},{"id":"google/gemini-3.1-flash-image-preview","displayName":"Nano Banana 2 (Gemini 3.1 Flash Image Preview)","provider":"Google","modalityIn":["image","text"],"modalityOut":["image","text"],"contextLength":131072,"inputPricePerM":0.5,"outputPricePerM":3,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.…","createdISO":"2026-02-26","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3.1-pro-preview-customtools","displayName":"Gemini 3.1 Pro Preview Custom Tools","provider":"Google","modalityIn":["text","audio","image","video","file"],"modalityOut":["text"],"contextLength":1048756,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient…","createdISO":"2026-02-25","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3.1-pro-preview","displayName":"Gemini 3.1 Pro Preview","provider":"Google","modalityIn":["audio","file","image","text","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage…","createdISO":"2026-02-19","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":46.5,"benchCoding":68.8,"benchAgentic":21.4,"unavailableReason":null},{"id":"anthropic/claude-sonnet-4-6","displayName":"Claude Sonnet 4.6","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":3,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex…","createdISO":"2026-02-17","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"benchIntelligence":47.2,"benchCoding":63,"benchAgentic":40.8,"unavailableReason":"no enabled provider key serves it"},{"id":"anthropic/claude-opus-4-6","displayName":"Claude Opus 4.6","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":5,"outputPricePerM":25,"knowledgeCutoff":null,"shortDescription":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts,…","createdISO":"2026-02-04","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p","verbosity"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-3-flash-preview","displayName":"Gemini 3 Flash Preview","provider":"Google","modalityIn":["text","image","file","audio","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.5,"outputPricePerM":3,"knowledgeCutoff":null,"shortDescription":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and…","createdISO":"2025-12-17","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65535,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/deep-research-pro-preview-12-2025","displayName":"Deep Research Pro Preview 12 2025","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Deep Research Pro Preview 12 2025 is served live on the gateway today (input: text).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-2.5-flash-native-audio-preview-12-2025","displayName":"Gemini 2.5 Flash Native Audio Preview 12 2025","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.5 Flash Native Audio Preview 12 2025 produces speech audio, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"anthropic/claude-opus-4-5-20251101","displayName":"Claude Opus 4.5","provider":"Anthropic","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":200000,"inputPricePerM":5,"outputPricePerM":25,"knowledgeCutoff":null,"shortDescription":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal…","createdISO":"2025-11-24","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":64000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","verbosity"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-3-pro-image-preview","displayName":"Nano Banana Pro (Gemini 3 Pro Image Preview)","provider":"Google","modalityIn":["image","text"],"modalityOut":["image","text"],"contextLength":65536,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal…","createdISO":"2025-11-20","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":32768,"tokenizer":"Gemini","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"anthropic/claude-haiku-4-5-20251001","displayName":"Claude Haiku 4.5","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":200000,"inputPricePerM":1,"outputPricePerM":5,"knowledgeCutoff":null,"shortDescription":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching…","createdISO":"2025-10-15","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":64000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":29.6,"benchCoding":43.9,"benchAgentic":16.4,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-2.5-flash-image","displayName":"Nano Banana (Gemini 2.5 Flash Image)","provider":"Google","modalityIn":["image","text"],"modalityOut":["image","text"],"contextLength":32768,"inputPricePerM":0.3,"outputPricePerM":2.5,"knowledgeCutoff":"2025-01-31","shortDescription":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image…","createdISO":"2025-10-07","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":8192,"tokenizer":"Gemini","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["max_tokens","response_format","seed","stop","structured_outputs","temperature","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-2.5-computer-use-preview-10-2025","displayName":"Gemini 2.5 Computer Use Preview 10 2025","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.5 Computer Use Preview 10 2025 is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"anthropic/claude-sonnet-4-5-20250929","displayName":"Claude Sonnet 4.5","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":3,"outputPricePerM":15,"knowledgeCutoff":"2025-01-31","shortDescription":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding…","createdISO":"2025-09-29","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":64000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":36.4,"benchCoding":52.1,"benchAgentic":24.6,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-2.5-flash-native-audio-preview-09-2025","displayName":"Gemini 2.5 Flash Native Audio Preview 09 2025","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.5 Flash Native Audio Preview 09 2025 produces speech audio, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-2.5-flash-lite","displayName":"Gemini 2.5 Flash Lite","provider":"Google","modalityIn":["text","image","file","audio","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.1,"outputPricePerM":0.4,"knowledgeCutoff":"2025-01-31","shortDescription":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token…","createdISO":"2025-07-22","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65535,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-2.5-flash","displayName":"Gemini 2.5 Flash","provider":"Google","modalityIn":["file","image","text","audio","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.3,"outputPricePerM":2.5,"knowledgeCutoff":"2025-01-31","shortDescription":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in…","createdISO":"2025-06-17","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65535,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-2.5-pro","displayName":"Gemini 2.5 Pro","provider":"Google","modalityIn":["text","image","file","audio","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":1.25,"outputPricePerM":10,"knowledgeCutoff":"2025-01-31","shortDescription":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to…","createdISO":"2025-06-17","matched":true,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Gemini","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":25.8,"benchCoding":33.3,"benchAgentic":7.1,"unavailableReason":null},{"id":"google/gemini-2.0-flash","displayName":"Gemini 2.0 Flash","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.0 Flash is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-2.0-flash-001","displayName":"Gemini 2.0 Flash 001","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.0 Flash 001 is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-2.0-flash-lite-001","displayName":"Gemini 2.0 Flash Lite 001","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.0 Flash Lite 001 is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-2.0-flash-lite","displayName":"Gemini 2.0 Flash Lite","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.0 Flash Lite is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-2.5-flash-preview-tts","displayName":"Gemini 2.5 Flash Preview TTS","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.5 Flash Preview TTS produces speech audio, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-2.5-pro-preview-tts","displayName":"Gemini 2.5 Pro Preview TTS","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.5 Pro Preview TTS produces speech audio, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no audio endpoint on this gateway"},{"id":"google/gemini-flash-lite-latest","displayName":"Gemini Flash Lite Latest","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini Flash Lite Latest is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3-pro-preview","displayName":"Gemini 3 Pro Preview","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 3 Pro Preview is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/nano-banana-pro-preview","displayName":"Nano Banana Pro Preview","provider":"Google","modalityIn":["text","image"],"modalityOut":["image"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Nano Banana Pro Preview generates and edits images, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no image endpoint on this gateway"},{"id":"google/gemini-3.1-flash-tts-preview","displayName":"Gemini 3.1 Flash TTS Preview","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Flash TTS Preview produces speech audio, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-robotics-er-1.5-preview","displayName":"Gemini Robotics ER 1.5 Preview","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini Robotics ER 1.5 Preview is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-robotics-er-1.6-preview","displayName":"Gemini Robotics ER 1.6 Preview","provider":"Google","modalityIn":["text","image","audio","video","file"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini Robotics ER 1.6 Preview is served live on the gateway today (input: text, image, audio, video, file).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-embedding-001","displayName":"Gemini Embedding 001","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini Embedding 001 is a text embedding model available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-embedding-2-preview","displayName":"Gemini Embedding 2 Preview","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini Embedding 2 Preview is a text embedding model available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-embedding-2","displayName":"Gemini Embedding 2","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini Embedding 2 is a text embedding model available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/aqa","displayName":"AQA","provider":"Google","modalityIn":["text"],"modalityOut":["text"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"AQA is an attributed question-answering model available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/imagen-4.0-generate-001","displayName":"Imagen 4.0 Generate 001","provider":"Google","modalityIn":["text","image"],"modalityOut":["image"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Imagen 4.0 Generate 001 generates and edits images, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/imagen-4.0-ultra-generate-001","displayName":"Imagen 4.0 Ultra Generate 001","provider":"Google","modalityIn":["text","image"],"modalityOut":["image"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Imagen 4.0 Ultra Generate 001 generates and edits images, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/imagen-4.0-fast-generate-001","displayName":"Imagen 4.0 Fast Generate 001","provider":"Google","modalityIn":["text","image"],"modalityOut":["image"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Imagen 4.0 Fast Generate 001 generates and edits images, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/veo-2.0-generate-001","displayName":"Veo 2.0 Generate 001","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Veo 2.0 Generate 001 generates video, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/veo-3.0-generate-001","displayName":"Veo 3.0 Generate 001","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Veo 3.0 Generate 001 generates video, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/veo-3.0-fast-generate-001","displayName":"Veo 3.0 Fast Generate 001","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Veo 3.0 Fast Generate 001 generates video, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/veo-3.1-generate-preview","displayName":"Veo 3.1 Generate Preview","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Veo 3.1 Generate Preview generates video, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/veo-3.1-fast-generate-preview","displayName":"Veo 3.1 Fast Generate Preview","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Veo 3.1 Fast Generate Preview generates video, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/veo-3.1-lite-generate-preview","displayName":"Veo 3.1 Lite Generate Preview","provider":"Google","modalityIn":["text","image"],"modalityOut":["video"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Veo 3.1 Lite Generate Preview generates video, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-2.5-flash-native-audio-latest","displayName":"Gemini 2.5 Flash Native Audio Latest","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 2.5 Flash Native Audio Latest produces speech audio, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-3.1-flash-live-preview","displayName":"Gemini 3.1 Flash Live Preview","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Flash Live Preview is served live on the gateway today (input: text).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/gemini-3.5-live-translate-preview","displayName":"Gemini 3.5 Live Translate Preview","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Gemini 3.5 Live Translate Preview is served live on the gateway today (input: text).","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"google/lyria-realtime-exp","displayName":"Lyria Realtime Exp","provider":"Google","modalityIn":["text"],"modalityOut":["audio"],"contextLength":0,"inputPricePerM":0,"outputPricePerM":0,"knowledgeCutoff":null,"shortDescription":"Lyria Realtime Exp generates audio and music, available on the gateway.","createdISO":null,"matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"sakana/fugu-ultra","displayName":"Fugu Ultra","provider":"Sakana AI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":5,"outputPricePerM":30,"knowledgeCutoff":null,"shortDescription":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model…","createdISO":"2026-06-24","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","reasoning","reasoning_effort","structured_outputs","tool_choice","tools","web_search_options"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"z-ai/glm-5.2","displayName":"GLM 5.2","provider":"Z.ai","modalityIn":["text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.95,"outputPricePerM":3,"knowledgeCutoff":null,"shortDescription":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level…","createdISO":"2026-06-16","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/zai-org","openSource":true,"maxOutputTokens":128000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":51.1,"benchCoding":68.8,"benchAgentic":43.1,"unavailableReason":"no enabled provider key serves it"},{"id":"moonshotai/kimi-k2.7-code","displayName":"Kimi K2.7 Code","provider":"Moonshot AI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.74,"outputPricePerM":3.5,"knowledgeCutoff":null,"shortDescription":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native…","createdISO":"2026-06-12","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/moonshotai","openSource":true,"maxOutputTokens":262144,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":41.9,"benchCoding":60.8,"benchAgentic":29.6,"unavailableReason":"no enabled provider key serves it"},{"id":"nex-agi/nex-n2-pro","displayName":"Nex-N2-Pro","provider":"Nex AGI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.25,"outputPricePerM":1,"knowledgeCutoff":null,"shortDescription":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input…","createdISO":"2026-06-08","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":262144,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":false,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","reasoning","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":41,"benchCoding":59.1,"benchAgentic":31},{"id":"nvidia/nemotron-3-ultra-550b-a55b","displayName":"Nemotron 3 Ultra","provider":"NVIDIA","modalityIn":["text"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.5,"outputPricePerM":2.2,"knowledgeCutoff":null,"shortDescription":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba…","createdISO":"2026-06-04","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":16384,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":37.8,"benchCoding":49.3,"benchAgentic":27.4},{"id":"qwen/qwen3.7-plus","displayName":"Qwen3.7 Plus","provider":"Qwen","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.32,"outputPricePerM":1.28,"knowledgeCutoff":null,"shortDescription":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a…","createdISO":"2026-06-03","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":39,"benchCoding":55.9,"benchAgentic":20.8},{"id":"minimax/minimax-m3","displayName":"MiniMax M3","provider":"MiniMax","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.3,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon…","createdISO":"2026-05-31","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/MiniMaxAI","openSource":true,"maxOutputTokens":512000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":44.4,"benchCoding":58.6,"benchAgentic":35.4},{"id":"stepfun/step-3.7-flash","displayName":"Step 3.7 Flash","provider":"StepFun","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.2,"outputPricePerM":1.15,"knowledgeCutoff":null,"shortDescription":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and…","createdISO":"2026-05-28","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":256000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":30.3,"benchCoding":39.6,"benchAgentic":21.5},{"id":"anthropic/claude-opus-4.8-fast","displayName":"Claude Opus 4.8 (Fast)","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":10,"outputPricePerM":50,"knowledgeCutoff":null,"shortDescription":"Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs:","createdISO":"2026-05-27","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.7-max","displayName":"Qwen3.7 Max","provider":"Qwen","modalityIn":["text"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":1.25,"outputPricePerM":3.75,"knowledgeCutoff":null,"shortDescription":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding,…","createdISO":"2026-05-21","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":46,"benchCoding":66,"benchAgentic":30.6,"unavailableReason":"no enabled provider key serves it"},{"id":"x-ai/grok-build-0.1","displayName":"Grok Build 0.1","provider":"xAI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":1,"outputPricePerM":2,"knowledgeCutoff":null,"shortDescription":"Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for…","createdISO":"2026-05-20","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":"Grok","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"benchIntelligence":39.8,"benchCoding":51.5,"benchAgentic":28},{"id":"anthropic/claude-opus-4.7-fast","displayName":"Claude Opus 4.7 (Fast)","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":30,"outputPricePerM":150,"knowledgeCutoff":null,"shortDescription":"Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs:","createdISO":"2026-05-12","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"Claude","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","tool_choice","tools","verbosity"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"perceptron/perceptron-mk1","displayName":"Perceptron Mk1","provider":"Perceptron","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":32768,"inputPricePerM":0.15,"outputPricePerM":1.5,"knowledgeCutoff":null,"shortDescription":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language…","createdISO":"2026-05-12","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":8192,"tokenizer":"Other","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","structured_outputs","temperature","top_k","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"inclusionai/ring-2.6-1t","displayName":"Ring-2.6-1T","provider":"Inclusion AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.075,"outputPricePerM":0.625,"knowledgeCutoff":null,"shortDescription":"Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency.…","createdISO":"2026-05-08","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":30.6,"benchCoding":42.8,"benchAgentic":18.9},{"id":"openai/gpt-chat-latest","displayName":"GPT Chat Latest","provider":"OpenAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":5,"outputPricePerM":30,"knowledgeCutoff":null,"shortDescription":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model…","createdISO":"2026-05-05","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"x-ai/grok-4.3","displayName":"Grok 4.3","provider":"xAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":1.25,"outputPricePerM":2.5,"knowledgeCutoff":null,"shortDescription":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications…","createdISO":"2026-04-30","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":"Grok","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"benchIntelligence":37.6,"benchCoding":42.2,"benchAgentic":24.1},{"id":"ibm-granite/granite-4.1-8b","displayName":"Granite 4.1 8B","provider":"IBM Granite","modalityIn":["text"],"modalityOut":["text"],"contextLength":131072,"inputPricePerM":0.05,"outputPricePerM":0.1,"knowledgeCutoff":null,"shortDescription":"Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for…","createdISO":"2026-04-30","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":9.5,"benchAgentic":null},{"id":"mistralai/mistral-medium-3-5","displayName":"Mistral Medium 3.5","provider":"Mistral AI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":1.5,"outputPricePerM":7.5,"knowledgeCutoff":null,"shortDescription":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding,…","createdISO":"2026-04-30","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/mistralai","openSource":true,"maxOutputTokens":null,"tokenizer":"Mistral","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":29.9,"benchCoding":46.9,"benchAgentic":19},{"id":"poolside/laguna-xs.2","displayName":"Laguna XS.2","provider":"Poolside","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.1,"outputPricePerM":0.2,"knowledgeCutoff":null,"shortDescription":"Laguna XS.2 is the second-generation model in the XS size class from Poolside, their efficient coding agent series. It combines tool calling and reasoning capabilities with a…","createdISO":"2026-04-28","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"poolside/laguna-m.1","displayName":"Laguna M.1","provider":"Poolside","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.2,"outputPricePerM":0.4,"knowledgeCutoff":null,"shortDescription":"Laguna M.1 is the flagship coding agent model from Poolside, optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and…","createdISO":"2026-04-28","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-plus-20260420","displayName":"Qwen3.5 Plus 2026-04-20","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.3,"outputPricePerM":1.8,"knowledgeCutoff":null,"shortDescription":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context…","createdISO":"2026-04-27","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.6-flash","displayName":"Qwen3.6 Flash","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.188,"outputPricePerM":1.125,"knowledgeCutoff":null,"shortDescription":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks…","createdISO":"2026-04-27","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.6-35b-a3b","displayName":"Qwen3.6 35B A3B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.14,"outputPricePerM":1,"knowledgeCutoff":null,"shortDescription":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse…","createdISO":"2026-04-27","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":262144,"tokenizer":"Qwen","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":31.6,"benchCoding":41.9,"benchAgentic":21.4},{"id":"qwen/qwen3.6-max-preview","displayName":"Qwen3.6 Max Preview","provider":"Qwen","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":1.04,"outputPricePerM":6.24,"knowledgeCutoff":null,"shortDescription":"Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is…","createdISO":"2026-04-27","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.6-27b","displayName":"Qwen3.6 27B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.26,"outputPricePerM":2.385,"knowledgeCutoff":null,"shortDescription":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text,…","createdISO":"2026-04-27","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":37.1,"benchCoding":53.7,"benchAgentic":27},{"id":"openai/gpt-5.5-pro","displayName":"GPT-5.5 Pro","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":1050000,"inputPricePerM":30,"outputPricePerM":180,"knowledgeCutoff":"2025-12-01","shortDescription":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K…","createdISO":"2026-04-24","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-5.5","displayName":"GPT-5.5","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":1050000,"inputPricePerM":5,"outputPricePerM":30,"knowledgeCutoff":"2025-12-01","shortDescription":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on…","createdISO":"2026-04-24","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":54.8,"benchCoding":74.9,"benchAgentic":44.9,"unavailableReason":"no enabled provider key serves it"},{"id":"deepseek/deepseek-v4-pro","displayName":"DeepSeek V4 Pro","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.435,"outputPricePerM":0.87,"knowledgeCutoff":null,"shortDescription":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is…","createdISO":"2026-04-24","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/deepseek-ai","openSource":true,"maxOutputTokens":384000,"tokenizer":"DeepSeek","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":44.3,"benchCoding":59.4,"benchAgentic":36.4,"unavailableReason":"no enabled provider key serves it"},{"id":"deepseek/deepseek-v4-flash","displayName":"DeepSeek V4 Flash","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.14,"outputPricePerM":0.28,"knowledgeCutoff":null,"shortDescription":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.…","createdISO":"2026-04-24","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/deepseek-ai","openSource":true,"maxOutputTokens":393216,"tokenizer":"DeepSeek","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"benchIntelligence":40.3,"benchCoding":56.2,"benchAgentic":31.1,"unavailableReason":"no enabled provider key serves it"},{"id":"inclusionai/ling-2.6-1t","displayName":"Ling-2.6-1T","provider":"Inclusion AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.075,"outputPricePerM":0.625,"knowledgeCutoff":null,"shortDescription":"Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high…","createdISO":"2026-04-23","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":32768,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"tencent/hy3-preview","displayName":"Hy3 preview","provider":"Tencent","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.063,"outputPricePerM":0.21,"knowledgeCutoff":null,"shortDescription":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across…","createdISO":"2026-04-22","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":false,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"benchIntelligence":41.2,"benchCoding":58.8,"benchAgentic":30.7},{"id":"xiaomi/mimo-v2.5-pro","displayName":"MiMo-V2.5-Pro","provider":"Xiaomi","modalityIn":["text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.435,"outputPricePerM":0.87,"knowledgeCutoff":null,"shortDescription":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on…","createdISO":"2026-04-22","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":42.2,"benchCoding":60.2,"benchAgentic":29.1},{"id":"xiaomi/mimo-v2.5","displayName":"MiMo-V2.5","provider":"Xiaomi","modalityIn":["text","audio","image","video"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.105,"outputPricePerM":0.28,"knowledgeCutoff":null,"shortDescription":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal…","createdISO":"2026-04-22","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":37.2,"benchCoding":56.8,"benchAgentic":23.7},{"id":"openai/gpt-5.4-image-2","displayName":"GPT-5.4 Image 2","provider":"OpenAI","modalityIn":["image","text","file"],"modalityOut":["image","text"],"contextLength":272000,"inputPricePerM":8,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to…","createdISO":"2026-04-21","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","top_logprobs"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"inclusionai/ling-2.6-flash","displayName":"Ling-2.6-flash","provider":"Inclusion AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.01,"outputPricePerM":0.03,"knowledgeCutoff":null,"shortDescription":"Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses,…","createdISO":"2026-04-21","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":32768,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":14.1,"benchCoding":25.3,"benchAgentic":2.3},{"id":"moonshotai/kimi-k2.6","displayName":"Kimi K2.6","provider":"Moonshot AI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.66,"outputPricePerM":3.41,"knowledgeCutoff":null,"shortDescription":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex…","createdISO":"2026-04-20","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/moonshotai","openSource":true,"maxOutputTokens":262144,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":44.2,"benchCoding":61.8,"benchAgentic":30.3,"unavailableReason":"no enabled provider key serves it"},{"id":"anthropic/claude-opus-4.6-fast","displayName":"Claude Opus 4.6 (Fast)","provider":"Anthropic","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":30,"outputPricePerM":150,"knowledgeCutoff":null,"shortDescription":"Fast-mode variant of Opus 4.6 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs:","createdISO":"2026-04-07","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"z-ai/glm-5.1","displayName":"GLM 5.1","provider":"Z.ai","modalityIn":["text"],"modalityOut":["text"],"contextLength":202752,"inputPricePerM":0.98,"outputPricePerM":3.08,"knowledgeCutoff":null,"shortDescription":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level…","createdISO":"2026-04-07","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/zai-org","openSource":true,"maxOutputTokens":128000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":40.2,"benchCoding":55.8,"benchAgentic":29.9,"unavailableReason":"no enabled provider key serves it"},{"id":"qwen/qwen3.6-plus","displayName":"Qwen3.6 Plus","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.325,"outputPricePerM":1.95,"knowledgeCutoff":null,"shortDescription":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance…","createdISO":"2026-04-02","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":39.6,"benchCoding":54.5,"benchAgentic":27.6},{"id":"z-ai/glm-5v-turbo","displayName":"GLM 5V Turbo","provider":"Z.ai","modalityIn":["image","text","video"],"modalityOut":["text"],"contextLength":202752,"inputPricePerM":1.2,"outputPricePerM":4,"knowledgeCutoff":null,"shortDescription":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs,…","createdISO":"2026-04-01","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/zai-org","openSource":true,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"arcee-ai/trinity-large-thinking","displayName":"Trinity Large Thinking","provider":"Arcee AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.25,"outputPricePerM":0.8,"knowledgeCutoff":null,"shortDescription":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks.…","createdISO":"2026-04-01","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":262144,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":18.2,"benchCoding":25.8,"benchAgentic":3.7},{"id":"x-ai/grok-4.20-multi-agent","displayName":"Grok 4.20 Multi-Agent","provider":"xAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":2000000,"inputPricePerM":1.25,"outputPricePerM":2.5,"knowledgeCutoff":"2025-09-01","shortDescription":"Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate…","createdISO":"2026-03-31","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":"Grok","supportsTools":false,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","logprobs","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","temperature","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"x-ai/grok-4.20","displayName":"Grok 4.20","provider":"xAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":2000000,"inputPricePerM":1.25,"outputPricePerM":2.5,"knowledgeCutoff":"2025-09-01","shortDescription":"Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict…","createdISO":"2026-03-31","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":"Grok","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","logprobs","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"kwaipilot/kat-coder-pro-v2","displayName":"KAT-Coder-Pro V2","provider":"Kwaipilot","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.3,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on…","createdISO":"2026-03-27","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Kwaipilot","openSource":true,"maxOutputTokens":80000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":33.7,"benchCoding":59.5,"benchAgentic":15.5},{"id":"rekaai/reka-edge","displayName":"Reka Edge","provider":"Reka AI","modalityIn":["image","text","video"],"modalityOut":["text"],"contextLength":16384,"inputPricePerM":0.1,"outputPricePerM":0.1,"knowledgeCutoff":null,"shortDescription":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to…","createdISO":"2026-03-20","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":16384,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logprobs","max_tokens","presence_penalty","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"minimax/minimax-m2.7","displayName":"MiniMax M2.7","provider":"MiniMax","modalityIn":["text"],"modalityOut":["text"],"contextLength":204800,"inputPricePerM":0.18,"outputPricePerM":0.72,"knowledgeCutoff":null,"shortDescription":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own…","createdISO":"2026-03-18","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/MiniMaxAI","openSource":true,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":38.1,"benchCoding":52.6,"benchAgentic":25.6},{"id":"openai/gpt-5.4-nano","displayName":"GPT-5.4 Nano","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":0.4,"outputPricePerM":2.5,"knowledgeCutoff":"2025-08-31","shortDescription":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is…","createdISO":"2026-03-17","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":38.2,"benchCoding":56.1,"benchAgentic":27.5,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-5.4-mini","displayName":"GPT-5.4 Mini","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":"2025-08-31","shortDescription":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong…","createdISO":"2026-03-17","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":40,"benchCoding":56.1,"benchAgentic":30.2,"unavailableReason":"no enabled provider key serves it"},{"id":"mistralai/mistral-small-2603","displayName":"Mistral Small 4","provider":"Mistral AI","modalityIn":["text","image"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.15,"outputPricePerM":0.6,"knowledgeCutoff":null,"shortDescription":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong…","createdISO":"2026-03-16","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/mistralai","openSource":true,"maxOutputTokens":null,"tokenizer":"Mistral","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","reasoning_effort","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":19.6,"benchCoding":26.6,"benchAgentic":4.7},{"id":"z-ai/glm-5-turbo","displayName":"GLM 5 Turbo","provider":"Z.ai","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":1.2,"outputPricePerM":4,"knowledgeCutoff":null,"shortDescription":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for…","createdISO":"2026-03-15","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/zai-org","openSource":true,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"nvidia/nemotron-3-super-120b-a12b","displayName":"Nemotron 3 Super","provider":"NVIDIA","modalityIn":["text"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.085,"outputPricePerM":0.4,"knowledgeCutoff":null,"shortDescription":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications.…","createdISO":"2026-03-11","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":16384,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":25.4,"benchCoding":37.7,"benchAgentic":8.7},{"id":"bytedance-seed/seed-2.0-lite","displayName":"Seed-2.0-Lite","provider":"ByteDance Seed","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.25,"outputPricePerM":2,"knowledgeCutoff":null,"shortDescription":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a…","createdISO":"2026-03-10","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-9b","displayName":"Qwen3.5-9B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.1,"outputPricePerM":0.15,"knowledgeCutoff":null,"shortDescription":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter…","createdISO":"2026-03-10","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":262144,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":21.4,"benchCoding":28.7,"benchAgentic":7.4},{"id":"openai/gpt-5.4-pro","displayName":"GPT-5.4 Pro","provider":"OpenAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1050000,"inputPricePerM":30,"outputPricePerM":180,"knowledgeCutoff":null,"shortDescription":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+…","createdISO":"2026-03-05","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5.4","displayName":"GPT-5.4","provider":"OpenAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":1050000,"inputPricePerM":2.5,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support…","createdISO":"2026-03-05","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":51.4,"benchCoding":71.1,"benchAgentic":41.1},{"id":"inception/mercury-2","displayName":"Mercury 2","provider":"Inception","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.25,"outputPricePerM":0.75,"knowledgeCutoff":null,"shortDescription":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple…","createdISO":"2026-03-04","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":50000,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools"],"benchIntelligence":21.4,"benchCoding":31.1,"benchAgentic":9.6},{"id":"openai/gpt-5.3-chat","displayName":"GPT-5.3 Chat","provider":"OpenAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":1.75,"outputPricePerM":14,"knowledgeCutoff":null,"shortDescription":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with…","createdISO":"2026-03-03","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":16384,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["max_completion_tokens","max_tokens","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"bytedance-seed/seed-2.0-mini","displayName":"Seed-2.0-Mini","provider":"ByteDance Seed","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.1,"outputPricePerM":0.4,"knowledgeCutoff":null,"shortDescription":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance…","createdISO":"2026-02-26","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","stop","structured_outputs","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-35b-a3b","displayName":"Qwen3.5-35B-A3B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.14,"outputPricePerM":1,"knowledgeCutoff":null,"shortDescription":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model,…","createdISO":"2026-02-25","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":262144,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":24,"benchCoding":37,"benchAgentic":11.8},{"id":"qwen/qwen3.5-27b","displayName":"Qwen3.5-27B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.195,"outputPricePerM":1.56,"knowledgeCutoff":null,"shortDescription":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its…","createdISO":"2026-02-25","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-122b-a10b","displayName":"Qwen3.5-122B-A10B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.26,"outputPricePerM":2.08,"knowledgeCutoff":null,"shortDescription":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving…","createdISO":"2026-02-25","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":32.3,"benchCoding":45.7,"benchAgentic":20.7},{"id":"qwen/qwen3.5-flash-02-23","displayName":"Qwen3.5-Flash","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.065,"outputPricePerM":0.26,"knowledgeCutoff":null,"shortDescription":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving…","createdISO":"2026-02-25","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"liquid/lfm-2-24b-a2b","displayName":"LFM2-24B-A2B","provider":"Liquid AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.03,"outputPricePerM":0.12,"knowledgeCutoff":null,"shortDescription":"LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with…","createdISO":"2026-02-25","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5.3-codex","displayName":"GPT-5.3-Codex","provider":"OpenAI","modalityIn":["text","image","file"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":1.75,"outputPricePerM":14,"knowledgeCutoff":null,"shortDescription":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional…","createdISO":"2026-02-24","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"aion-labs/aion-2.0","displayName":"Aion-2.0","provider":"Aion Labs","modalityIn":["text"],"modalityOut":["text"],"contextLength":131072,"inputPricePerM":0.8,"outputPricePerM":1.6,"knowledgeCutoff":null,"shortDescription":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories,…","createdISO":"2026-02-23","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":32768,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_tokens","reasoning","response_format","temperature","tool_choice","tools","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-plus-02-15","displayName":"Qwen3.5 Plus 2026-02-15","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":1000000,"inputPricePerM":0.26,"outputPricePerM":1.56,"knowledgeCutoff":null,"shortDescription":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models,…","createdISO":"2026-02-16","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-397b-a17b","displayName":"Qwen3.5 397B A17B","provider":"Qwen","modalityIn":["text","image","video"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.385,"outputPricePerM":2.45,"knowledgeCutoff":null,"shortDescription":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model,…","createdISO":"2026-02-16","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen3","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":33.7,"benchCoding":48.2,"benchAgentic":19.8},{"id":"minimax/minimax-m2.5","displayName":"MiniMax M2.5","provider":"MiniMax","modalityIn":["text"],"modalityOut":["text"],"contextLength":204800,"inputPricePerM":0.12,"outputPricePerM":0.48,"knowledgeCutoff":null,"shortDescription":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon…","createdISO":"2026-02-12","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/MiniMaxAI","openSource":true,"maxOutputTokens":196608,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","parallel_tool_calls","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"z-ai/glm-5","displayName":"GLM 5","provider":"Z.ai","modalityIn":["text"],"modalityOut":["text"],"contextLength":202752,"inputPricePerM":0.6,"outputPricePerM":1.92,"knowledgeCutoff":null,"shortDescription":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers…","createdISO":"2026-02-11","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/zai-org","openSource":true,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"qwen/qwen3-max-thinking","displayName":"Qwen3 Max Thinking","provider":"Qwen","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.78,"outputPricePerM":3.9,"knowledgeCutoff":null,"shortDescription":"Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling…","createdISO":"2026-02-09","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":65536,"tokenizer":"Qwen","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logprobs","max_tokens","presence_penalty","reasoning","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3-coder-next","displayName":"Qwen3 Coder Next","provider":"Qwen","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.11,"outputPricePerM":0.8,"knowledgeCutoff":null,"shortDescription":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and…","createdISO":"2026-02-04","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":262144,"tokenizer":"Qwen","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":21.1,"benchCoding":36.2,"benchAgentic":8.8},{"id":"openai/gpt-4o","displayName":"GPT-4o","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":2.5,"outputPricePerM":10,"knowledgeCutoff":"2023-10-31","shortDescription":"GPT-4o — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":16384,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-4o-mini","displayName":"GPT-4o mini","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.15,"outputPricePerM":0.6,"knowledgeCutoff":"2023-10-31","shortDescription":"GPT-4o mini — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":16384,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":false,"supportedParameters":["frequency_penalty","logit_bias","logprobs","max_completion_tokens","max_tokens","prediction","presence_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_logprobs","top_p","web_search_options"],"benchIntelligence":null,"benchCoding":11.4,"benchAgentic":1},{"id":"openai/chatgpt-4o-latest","displayName":"ChatGPT-4o (latest)","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":5,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"ChatGPT-4o (latest) — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at premium rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5-2","displayName":"GPT-5.2","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":1.25,"outputPricePerM":10,"knowledgeCutoff":null,"shortDescription":"GPT-5.2 — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":128000,"tokenizer":"GPT","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["include_reasoning","max_completion_tokens","max_tokens","reasoning","reasoning_effort","response_format","seed","structured_outputs","tool_choice","tools"],"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5-2-instant","displayName":"GPT-5.2 Instant","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.5,"outputPricePerM":4,"knowledgeCutoff":null,"shortDescription":"GPT-5.2 Instant — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5.2-all","displayName":"GPT-5.2 All","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":1.5,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"GPT-5.2 All — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5.2-chat-latest","displayName":"GPT-5.2 Chat (latest)","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":1.25,"outputPricePerM":10,"knowledgeCutoff":null,"shortDescription":"GPT-5.2 Chat (latest) — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-5.3-chat-latest","displayName":"GPT-5.3 Chat (latest)","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":1.5,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"GPT-5.3 Chat (latest) — a chat model from OpenAI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"x-ai/grok-4","displayName":"Grok 4","provider":"xAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":3,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"Grok 4 — a chat model from xAI, callable today through SuperbAPI's OpenAI-compatible endpoint at premium rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"x-ai/grok-4-1-auto","displayName":"Grok 4.1 Auto","provider":"xAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":3,"outputPricePerM":15,"knowledgeCutoff":null,"shortDescription":"Grok 4.1 Auto — a chat model from xAI, callable today through SuperbAPI's OpenAI-compatible endpoint at premium rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"x-ai/grok-4-2","displayName":"Grok 4.2","provider":"xAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":5,"outputPricePerM":25,"knowledgeCutoff":null,"shortDescription":"Grok 4.2 — a chat model from xAI, callable today through SuperbAPI's OpenAI-compatible endpoint at premium rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"deepseek/deepseek-r1","displayName":"DeepSeek R1","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.55,"outputPricePerM":2.2,"knowledgeCutoff":"2024-07-31","shortDescription":"DeepSeek R1 — a chat model from DeepSeek, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/deepseek-ai","openSource":true,"maxOutputTokens":16000,"tokenizer":"DeepSeek","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","max_completion_tokens","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"benchIntelligence":18.5,"benchCoding":24.6,"benchAgentic":3.1},{"id":"deepseek/deepseek-v3","displayName":"DeepSeek V3","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.3,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"DeepSeek V3 — a chat model from DeepSeek, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/deepseek-ai","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"deepseek/deepseek-v3.1","displayName":"DeepSeek V3.1","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.3,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"DeepSeek V3.1 — a chat model from DeepSeek, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/deepseek-ai","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"deepseek/deepseek-v3.2","displayName":"DeepSeek V3.2","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.3,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"DeepSeek V3.2 — a chat model from DeepSeek, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/deepseek-ai","openSource":true,"maxOutputTokens":65536,"tokenizer":"DeepSeek","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":32,"benchCoding":44.2,"benchAgentic":18.3},{"id":"z-ai/glm-4.7","displayName":"GLM-4.7","provider":"Z.ai","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.6,"outputPricePerM":2.2,"knowledgeCutoff":null,"shortDescription":"GLM-4.7 — a chat model from Z.ai, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/zai-org","openSource":true,"maxOutputTokens":131072,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":33.7,"benchCoding":45.3,"benchAgentic":25.4},{"id":"moonshotai/kimi-k2.5","displayName":"Kimi K2.5","provider":"Moonshot AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.6,"outputPricePerM":2.5,"knowledgeCutoff":null,"shortDescription":"Kimi K2.5 — a chat model from Moonshot AI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"sourceUrl":"https://huggingface.co/moonshotai","openSource":true,"maxOutputTokens":262144,"tokenizer":"Other","supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"benchIntelligence":35.4,"benchCoding":46.8,"benchAgentic":21.7,"unavailableReason":"no enabled provider key serves it"},{"id":"moonshotai/kimi-k2.5-thinking","displayName":"Kimi K2.5 Thinking","provider":"Moonshot AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.6,"outputPricePerM":2.5,"knowledgeCutoff":null,"shortDescription":"Kimi K2.5 Thinking — a chat model from Moonshot AI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"sourceUrl":"https://huggingface.co/moonshotai","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"moonshotai/kimi-for-coding","displayName":"Kimi for Coding","provider":"Moonshot AI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":0.6,"outputPricePerM":2.5,"knowledgeCutoff":null,"shortDescription":"Kimi for Coding — a chat model from Moonshot AI, callable today through SuperbAPI's OpenAI-compatible endpoint at standard rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"sourceUrl":"https://huggingface.co/moonshotai","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"minimax/minimax-m2.5-highspeed","displayName":"MiniMax M2.5 Highspeed","provider":"MiniMax","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.3,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"MiniMax M2.5 Highspeed — a chat model from MiniMax, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":true,"sourceUrl":"https://huggingface.co/MiniMaxAI","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"minimax/minimax-m2.7-highspeed","displayName":"MiniMax M2.7 Highspeed","provider":"MiniMax","modalityIn":["text"],"modalityOut":["text"],"contextLength":128000,"inputPricePerM":0.4,"outputPricePerM":1.6,"knowledgeCutoff":null,"shortDescription":"MiniMax M2.7 Highspeed — a chat model from MiniMax, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/MiniMaxAI","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"qwen/qwen3.5-plus","displayName":"Qwen3.5 Plus","provider":"Qwen","modalityIn":["text"],"modalityOut":["text"],"contextLength":262144,"inputPricePerM":0.4,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"Qwen3.5 Plus — a chat model from Qwen, callable today through SuperbAPI's OpenAI-compatible endpoint at budget rates.","createdISO":"2026-07-06","matched":true,"available":false,"availableNow":false,"newest":false,"sourceUrl":"https://huggingface.co/Qwen","openSource":true,"maxOutputTokens":null,"tokenizer":null,"supportsTools":null,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null},{"id":"openai/gpt-6-astra","displayName":"GPT-6 Astra","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":10,"outputPricePerM":50,"knowledgeCutoff":null,"shortDescription":"GPT-6 Astra is OpenAI's newest frontier model, built for long-horizon agentic work and complex reasoning. Priced for flagship use; supports a 272K-token short-context tier.","createdISO":"2026-09-01","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":128000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-5.6-sol","displayName":"GPT-5.6 Sol","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":5,"outputPricePerM":30,"knowledgeCutoff":null,"shortDescription":"GPT-5.6 Sol is the high-capability tier of the 5.6 line, tuned for demanding reasoning and coding work.","createdISO":"2026-08-20","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":128000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-5.6-terra","displayName":"GPT-5.6 Terra","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"GPT-5.6 Terra balances cost and capability in the 5.6 line — the general-purpose choice for everyday production traffic.","createdISO":"2026-08-20","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":128000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-5.6-luna","displayName":"GPT-5.6 Luna","provider":"OpenAI","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":400000,"inputPricePerM":0.2,"outputPricePerM":1.2,"knowledgeCutoff":null,"shortDescription":"GPT-5.6 Luna is the low-cost tier of the 5.6 line, for high-volume classification, extraction and routing.","createdISO":"2026-08-20","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":128000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"openai/gpt-3.5-turbo","displayName":"GPT-3.5 Turbo","provider":"OpenAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":16385,"inputPricePerM":0.5,"outputPricePerM":1.5,"knowledgeCutoff":null,"shortDescription":"GPT-3.5 Turbo remains a cheap, fast option for simple chat and classification workloads.","createdISO":"2023-03-01","matched":false,"available":false,"availableNow":false,"newest":false,"openSource":false,"maxOutputTokens":4096,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"anthropic/claude-sonnet-5","displayName":"Claude Sonnet 5","provider":"Anthropic","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":200000,"inputPricePerM":2,"outputPricePerM":10,"knowledgeCutoff":null,"shortDescription":"Claude Sonnet 5 is Anthropic's balanced model — near-frontier quality at a mid-tier price, with strong coding and tool use.","createdISO":"2026-08-15","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":64000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"x-ai/grok-4.6","displayName":"Grok 4.6","provider":"xAI","modalityIn":["text"],"modalityOut":["text"],"contextLength":256000,"inputPricePerM":2,"outputPricePerM":6,"knowledgeCutoff":null,"shortDescription":"Grok 4.6 is xAI's latest reasoning model, with a cheaper short-context tier below 200K tokens.","createdISO":"2026-08-25","matched":false,"available":false,"availableNow":false,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":64000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":null,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"deepseek/deepseek-v4-pro-0813","displayName":"DeepSeek V4 Pro","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":4.5,"outputPricePerM":13.5,"knowledgeCutoff":null,"shortDescription":"DeepSeek V4 Pro is a high-performance open model with strong reasoning and agent ability over a 1M-token context.","createdISO":"2026-08-13","matched":false,"available":false,"availableNow":false,"newest":false,"openSource":true,"maxOutputTokens":384000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"deepseek/deepseek-v4-flash-0731","displayName":"DeepSeek V4 Flash","provider":"DeepSeek","modalityIn":["text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":1.5,"outputPricePerM":4.5,"knowledgeCutoff":null,"shortDescription":"DeepSeek V4 Flash is the fast, cheaper sibling of V4 Pro for high-volume work over long contexts.","createdISO":"2026-07-31","matched":false,"available":false,"availableNow":false,"newest":false,"openSource":true,"maxOutputTokens":384000,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":null,"supportsReasoning":null,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":"no enabled provider key serves it"},{"id":"google/gemini-3.1-pro","displayName":"Gemini 3.1 Pro","provider":"Google","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":2,"outputPricePerM":12,"knowledgeCutoff":null,"shortDescription":"Gemini 3.1 Pro is Google's long-context reasoning model, serving the stable (non-preview) id.","createdISO":"2026-05-01","matched":false,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3.6-flash","displayName":"Gemini 3.6 Flash","provider":"Google","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.75,"outputPricePerM":3.75,"knowledgeCutoff":null,"shortDescription":"Gemini 3.6 Flash is a fast, low-cost long-context model for high-throughput production traffic.","createdISO":"2026-06-15","matched":false,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3.7-flash","displayName":"Gemini 3.7 Flash","provider":"Google","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":1.5,"outputPricePerM":7.5,"knowledgeCutoff":null,"shortDescription":"Gemini 3.7 Flash raises quality over 3.6 while keeping the Flash latency profile.","createdISO":"2026-07-15","matched":false,"available":true,"availableNow":true,"newest":false,"openSource":false,"maxOutputTokens":65536,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null},{"id":"google/gemini-3.8-flash","displayName":"Gemini 3.8 Flash","provider":"Google","modalityIn":["file","image","text"],"modalityOut":["text"],"contextLength":1048576,"inputPricePerM":0.75,"outputPricePerM":3.75,"knowledgeCutoff":null,"shortDescription":"Gemini 3.8 Flash is Google's newest Flash-tier model, with the same low pricing as 3.6.","createdISO":"2026-08-20","matched":false,"available":true,"availableNow":true,"newest":true,"newUntil":"2026-09-20","openSource":false,"maxOutputTokens":65536,"tokenizer":null,"supportsTools":true,"supportsStructuredOutputs":true,"supportsReasoning":true,"supportedParameters":null,"benchIntelligence":null,"benchCoding":null,"benchAgentic":null,"unavailableReason":null}],"availabilityComputedAt":"2026-10-27T04:29:55.873Z"}