Big-AGI Logo
BIG-AGI

BEAM

Models

Features

Rankings

Docs

New

Pro

LAUNCH APP

The Big-AGI Model Index

Supported AI models.

If it's on this list, it runs in Big-AGI. Capabilities, context windows, and pricing for every model. Your key, provider rates, no markup.

Alibaba

Anthropic

AWS Bedrock

Azure

Cerebras

DeepSeek

Fireworks AI

Google Gemini

Groq

Meta

MiniMax

Mistral

Modular

Moonshot

NVIDIA

OpenAI

OpenRouter

Perplexity

Sakana AI

SpaceXAI

Together AI

Z.ai

805 models indexed·800+ supported·refreshed hourly

What this list is: the models Big-AGI indexes, with full specs for each. Big-AGI also connects to any OpenAI-compatible endpoint, every model on OpenRouter, and local runtimes like Ollama, so the models you can run go beyond this list.

Available on
Highlights
Capabilities
SortVendorsCapabilities
Particle AI: Particle-1NEWParticle-1 is a token-efficient agentic coding model from Parti…1M$0.05$0.50VisionReasoningTools / functionsWeb searchOct 2026Ultramarine 1 Flash Us (Vision)deprecatedFine-tuned adapter served on Fireworks AI.1M--VisionOct 2026OpenAI: GPT-6.1 Terra ProNEWGPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra…1.1M$1.00$5.00VisionReasoningTools / functionsWeb searchOct 2026GPT-6.1 TerraNEWFast visual reasoning, computer use, and writing at half the pr…1.1M$1.00$5.00VisionReasoningTools / functionsWeb searchImage outputOct 2026Kimi K3.1 Pro HighspeedNEWHigh-speed K3.1 Pro: same model at about 2-3x the output speed.…1M$4.00$20.00VisionReasoningTools / functionsOct 2026Kimi K3.1 ProNEWMost capable flagship: K3 with scaled-up post-training, stronge…1M$2.00$10.00VisionReasoningTools / functionsOct 2026Recursive: Flint (free)NEWFlint is an open-weight mixture-of-experts model from Recursive…262KFreeFreeReasoningTools / functionsWeb searchOct 2026MiniMax M3.1 FlashNEWHOTEfficient open-weight M-series model for agentic reasoning, too…1M$0.15$0.60VisionReasoningTools / functionsOct 2026Elorian: GlimpseNEWGlimpse is a multimodal visual reasoning model from Elorian, bu…262K$0.60$3.00VisionReasoningTools / functionsWeb searchOct 2026DeepSeek: DeepSeek V4.1 Flash 1017NEWHOTDeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of De…1M$0.02$0.19VisionReasoningTools / functionsWeb searchOct 2026DeepSeek V4.1 Flash 1017 Spot (Vision)NEWOpen-weights model served on Fireworks AI.1M--VisionTools / functionsOct 2026DeepSeek V4.1 Flash 1017 (Vision)NEWPost-training update of DeepSeek V4.1 Flash (552B multimodal Mo…1M$0.30$1.20VisionReasoningTools / functionsOct 2026XingChen: Xing4.0 29B A4B (free)NEWXing4.0-29B-A4B is an open-weight mixture-of-experts language m…262KFreeFreeReasoningTools / functionsWeb searchOct 2026Reflection: Beam 1.0 501B A23BNEWBeam 1.0 is Reflection's open-weight reasoning model for coding…1M$0.25$1.00ReasoningTools / functionsWeb searchOct 2026PrismML: Ternary Bonsai 2 9BNEWTernary Bonsai 2 9B is PrismML’s compact, open-weight language…262K$0.08$0.13VisionReasoningTools / functionsWeb searchOct 2026Inception: Mercury 3NEWMercury 3 is a diffusion-based language model from Inception, a…1M$0.10$0.35ReasoningTools / functionsWeb searchOct 2026Pareto 26.10NEWPareto is a multimodal composite model built for research, codi…1M$0.80$3.20VisionTools / functionsWeb searchOct 2026NVIDIA: Nemotron 3.5 Super VLNEWHOTNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-e…1M$0.15$0.50VisionReasoningTools / functionsWeb searchOct 2026NVIDIA Nemotron 3.5 Super VLNEWNVIDIA chat model.262K$0.15$0.50VisionOct 2026Nemotron 3.5 Super VL 120BNEWNemotron 3.5 Super early access: multimodal MoE (120B, 12B acti…1MFreeFreeVisionReasoningTools / functionsOct 2026Muse Spark Open 816B A42BNEWMeta chat model.1M$1.25$4.25VisionOct 2026Moondream: Moondream 3.1NEWMoondream 3.1 is a vision-language model from Moondream, the su…32K$0.30$2.50VisionReasoningWeb searchOct 2026Moondream: Moondream 3 PreviewNEWMoondream 3 Preview is a vision-language model from Moondream w…32K$0.30$2.50VisionReasoningWeb searchOct 2026Meta: Muse Spark OpenNEWMuse Spark Open is a coding-optimized open-weight model. Traine…1M$1.25$4.25VisionReasoningTools / functionsWeb searchOct 2026ScaleDown: SummarizeNEWSummarize is an abstractive summarization model from ScaleDown.…1M$0.04FreeVisionWeb searchOct 2026ScaleDown: ExtractNEWExtract is a description-driven entity extraction model from Sc…1M$0.04FreeVisionWeb searchOct 2026Pareto 26.9NEWPareto is a multimodal composite model built for research, codi…262K$2.50$7.50VisionTools / functionsWeb searchOct 2026LiquidAI: LFM2.5-24B-A2BNEWLFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liq…128K$0.05$0.70ReasoningTools / functionsWeb searchOct 2026Muse Wonder 1.0NEWMeta's most capable model (preview), for complex software engin…1M$4.00$20.00VisionReasoningTools / functionsWeb searchOct 2026Meta: Muse WonderNEWMuse Wonder is a frontier reasoning model from Meta, designed f…1M$4.00$20.00VisionReasoningTools / functionsWeb searchOct 2026StepFun: Step 5 PreviewNEWStep 5 Preview is StepFun's flagship model for agentic work, bu…1M$1.00$2.70VisionReasoningTools / functionsWeb searchOct 2026Claude Haiku 5.5NEWHOTFastest model, for high-volume and latency-sensitive tasks1M$0.10$0.50VisionReasoningTools / functionsWeb searchOct 2026Nano Banana 2.1NEWGemini Nano Banana 2.1.131K$1.50$7.50VisionReasoningTools / functionsWeb searchImage outputOct 2026Mistral Large 4NEWMistral Large 4.01M$1.36$4.18VisionReasoningTools / functionsOct 2026inclusionAI: Ling 3.1 FlashNEWLing 3.1 Flash is a hybrid reasoning mixture-of-experts model f…1M$0.08$0.23ReasoningTools / functionsWeb searchOct 2026Pareto 26.10 PreviewdeprecatedPareto is a multimodal composite model built for research, codi…1M$0.80$3.20VisionTools / functionsWeb searchOct 2026Apodex: Apodex 1.1 Mini (free)deprecatedApodex 1.1 Mini is a reasoning-first model from Apodex, built f…262KFreeFreeReasoningTools / functionsWeb searchOct 2026Gemini 4 ArgonNEWHOTGemini 4 Argon1.1M$2.00$10.00VisionReasoningTools / functionsWeb searchSep 2026OpenAI: GPT-6.1 Sol ProNEWGPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, se…1.1M$2.00$10.00VisionReasoningTools / functionsWeb searchSep 2026GPT-6.1 SolNEWNear-Astra coding, computer use, and professional work at a fif…1.1M$2.00$10.00VisionReasoningTools / functionsWeb searchImage outputSep 2026Claude Sonnet 5.5NEWHOTBest combination of speed and intelligence1M$2.00$10.00VisionReasoningTools / functionsWeb searchSep 2026MiniMax M3.1 Flash (Preview, M Plan)deprecatedLatest M-series model for agentic reasoning, tool use, coding a…1M--VisionReasoningTools / functionsSep 2026TypeSafe: Jev RouterNEWJev Router picks the best model and reasoning effort for each r…1M--VisionReasoningTools / functionsWeb searchSep 2026Perceptron: Perceptron Mk1.5NEWPerceptron Mk1.5 is Perceptron's embodied reasoning model for p…37K$0.15$1.50VisionReasoningTools / functionsWeb searchSep 2026Fireworks: Ember-1NEWEmber-1 is a specialized reasoning model from Fireworks Researc…1M$3.00$15.00VisionReasoningTools / functionsWeb searchSep 2026Z.ai: GLM 5.3 PrimeNEWHOTGLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inhe…1M$2.80$8.80ReasoningTools / functionsWeb searchSep 2026Upstage: Solar Mini 4NEWSolar Mini 4 is Upstage's compact, cost-efficient language mode…524K$0.05$0.20ReasoningTools / functionsWeb searchSep 2026Space Bunny AlphadeprecatedSpace Bunny Alpha is an anonymous large model with blazing-fast…1MFreeFreeVisionReasoningTools / functionsWeb searchSep 2026Qwen: Qwen3.8 Max PrimeNEWQwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max…1M$4.00$12.00VisionReasoningTools / functionsWeb searchSep 2026AionLabs: Aion 3.5 MiniNEWHOTAion 3.5 Mini is a multi-model roleplaying and storytelling sys…262K$0.70$1.40ReasoningTools / functionsWeb searchSep 2026AionLabs: Aion 3.5NEWAion 3.5 is a multi-model roleplaying and storytelling system f…262K$3.00$6.00ReasoningTools / functionsWeb searchSep 2026OpenAI: GPT-6 Sol ProNEWGPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served…1.1M$2.00$10.00VisionReasoningTools / functionsWeb searchSep 2026OpenAI: GPT-6 Luna ProNEWGPT-6 Luna Pro is the same underlying model as GPT-6 Luna, serv…1.1M$0.10$0.50VisionReasoningTools / functionsWeb searchSep 2026GPT-6 SolNEWMiddle GPT-6 tier, below Astra: complex coding and agentic work…1.1M$2.00$10.00VisionReasoningTools / functionsWeb searchImage outputSep 2026GPT-6 LunaNEWLowest-cost GPT-6 tier, for focused, high-volume tasks. Succeed…1.1M$0.10$0.50VisionReasoningTools / functionsWeb searchImage outputSep 2026Gemini 3.8 Flash-Lite TTSNEWGemini 3.8 Flash Lite TTS25K$0.50$6.00VisionAudio outputSep 2026Gemini 3.8 Flash TTSNEWGemini 3.8 Flash TTS25K$0.50$9.00VisionAudio outputSep 2026Cohere: Command A+NEWCommand A+ is Cohere's flagship model for enterprise agentic wo…192K$0.30$1.50VisionReasoningTools / functionsWeb searchSep 2026Claude Opus 5.5NEWHOTFor long-running agentic coding and knowledge work1M$4.00$20.00VisionReasoningTools / functionsWeb searchSep 2026Xiaomi: MiMo-V2.6-Pro-UltraSpeedNEWMiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's…1M$4.35$8.70VisionReasoningTools / functionsWeb searchSep 2026Xiaomi: MiMo-V2.6-ProNEWMiMo-V2.6-Pro is the flagship foundation model developed by Xia…1.1M$0.44$0.87VisionReasoningTools / functionsWeb searchSep 2026Xiaomi: MiMo-V2.6-FlashNEWMiMo-V2.6-Flash is an open-source foundation model developed by…1.1M$0.14$0.28VisionReasoningTools / functionsWeb searchSep 2026Qwen: Qwen3.8 Omni FlashNEWQwen3.8 Omni Flash is an omni-modal reasoning model from Alibab…1M$0.15$0.47VisionReasoningTools / functionsWeb searchSep 2026NVIDIA: SwitchyardNEWSwitchyard is an open-source model routing system that switches…1M--Web searchSep 2026Grok 4.7NEWxAI's frontier model for coding, agentic tasks, and knowledge w…500K$2.00$6.00VisionReasoningTools / functionsWeb searchSep 2026Antigravity Agent Preview LatestdeprecatedLatest preview release of Antigravity Agent1.1M--VisionTools / functionsSep 2026PrismML: Ternary Bonsai 2 27BNEWBonsai 2 27B is a 27B-parameter reasoning model from PrismML de…262K$0.08$0.50VisionReasoningTools / functionsWeb searchSep 2026GLM-5.3 FlashX (1M)NEWFast GLM-5.3 Flash variant served at ~200 tokens/s. Image input…1M$0.37$1.25VisionReasoningTools / functionsSep 2026ParetodeprecatedPareto is a multimodal composite model built for research, codi…262K$2.50$7.50VisionTools / functionsWeb searchSep 2026Union AlphadeprecatedUnion Alpha is a multimodal model built for research, coding, a…262KFreeFreeVisionTools / functionsWeb searchSep 2026Antigravity Agent Preview (2026-09)Preview release of Antigravity Agent (09-2026)1.1M$0.75$3.75VisionReasoningSep 2026Inference.net: Schematron V2 TurboSchematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction m…128K$0.03$0.15Web searchSep 2026Inference.net: Schematron V2 SmallSchematron V2 Small is a 3B-parameter HTML-to-JSON extraction m…128K$0.05$0.23Web searchSep 2026Sakana: Fugu Ultra v2Fugu Ultra v2 is the higher-performance model in Sakana AI's Fu…1M$5.00$30.00VisionReasoningTools / functionsWeb searchSep 2026Sakana Fugu Ultra v2.0Multi-agent conductor system routing a deeper pool of expert ag…1M$5.00$30.00VisionReasoningTools / functionsWeb searchSep 2026Sakana Fugu Max v1.0Cost-optimized multi-agent orchestrator over Sakana's largest m…1M$2.00$6.00VisionReasoningTools / functionsWeb searchSep 2026Sakana Fugu MaxCost-optimized multi-agent orchestrator over Sakana's largest m…1M$2.00$6.00VisionReasoningTools / functionsWeb searchSep 2026

CO

North Small TranslatedeprecatedTranslation MoE (218B total, 25B active, CC BY-NC 4.0) from Coh…33K--Sep 2026inclusionAI: Ling 3.0 Flash VLLing 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B a…131K$0.06$0.18VisionReasoningTools / functionsWeb searchSep 2026DeepSeek V4.1 Flash Spot (Vision)Open-weights model served on Fireworks AI.1M--VisionTools / functionsSep 2026DeepSeek V4.1 Flash (Vision)DeepSeek multimodal MoE (552B, 8B active on input) with native…1M$0.30$1.20VisionReasoningTools / functionsSep 2026+1DeepSeek V4.1 Flash (1017)HOTMultimodal MoE (552B, 8B active on input) with 1M context and n…1M$0.30$1.20VisionReasoningTools / functionsSep 2026Nex AGI: Nex-N2.5-ProNex-N2.5 is an agentic model built to turn goals into working,…262K$0.08$0.25VisionReasoningTools / functionsWeb searchSep 2026Nex AGI: Nex-N2.5-MiniNex-N2.5 is an agentic model built to turn goals into working,…262K$0.03$0.10VisionReasoningWeb searchSep 2026Inception: Mercury 2.5Mercury 2.5 is the fastest reasoning LLM, and the latest diffus…260K$0.04$0.15ReasoningTools / functionsWeb searchSep 2026DeepSeek V4.1 Flash (beta)deprecatedIntermediate V4.1 release with a new model structure and native…1M$0.44$1.32VisionReasoningTools / functionsSep 2026inclusionAI: Ling 3.0 Flash SantedeprecatedLing 3.0 Flash Sante is a health and medicine-focused mixture-o…262K$0.04$0.12ReasoningTools / functionsWeb searchSep 2026OpenAI: GPT-6 Astra ProGPT-6 Astra Pro is the same underlying model as GPT-6 Astra, se…1.1M$10.00$50.00VisionReasoningTools / functionsWeb searchSep 2026GPT-6 AstraMost capable OpenAI model, built for the hardest end-to-end wor…1.1M$10.00$50.00VisionReasoningTools / functionsWeb searchImage outputSep 2026Qwen3.8 Max 0902Upgraded 0902 snapshot of Qwen3.8 Max: stronger engineering-sca…1M$2.00$6.00VisionReasoningTools / functionsSep 2026Meta: Muse Spark 1.3 ContributorMuse Spark 1.3 Contributor is the cost-efficient contributor ti…1M$0.10$0.20VisionReasoningTools / functionsWeb searchSep 2026Meta: Muse Spark 1.3Muse Spark 1.3 is a multimodal reasoning model from Meta for lo…1M$1.25$4.25VisionReasoningTools / functionsWeb searchSep 2026Gemini Flash LatestdeprecatedLatest release of Gemini Flash1.1M--VisionTools / functionsSep 2026Gemini 3.8 FlashHOTGemini 3.8 Flash1.1M$0.75$3.75VisionReasoningTools / functionsWeb searchSep 2026Claude Fable 5.1Most capable widely released model for demanding reasoning and…1M$10.00$50.00VisionReasoningTools / functionsWeb searchSep 2026Inception: Mercury 2.5 PreviewdeprecatedMercury 2.5 is the fastest reasoning LLM, and the latest diffus…260K$0.20$0.75ReasoningTools / functionsWeb searchAug 2026IBM: Granite 4.2 8BGranite 4.2 8B is a dense reasoning model from IBM. It is suite…131K$0.06$0.15ReasoningTools / functionsWeb searchAug 2026Tencent: Hy4 previewTencent: Hy4 preview is a mixture-of-experts model from Tencent…1M$0.83$2.50ReasoningTools / functionsWeb searchAug 2026GLM 5.3 SpotOpen-weights model served on Fireworks AI.1M--Tools / functionsAug 2026inclusionAI: Ling 3.0 Flash FindeprecatedLing 3.0 Flash Fin is a finance-focused mixture-of-experts mode…262K$0.04$0.12ReasoningTools / functionsWeb searchAug 2026Gemini Omni 1.1 Flash (video)Gemini Omni 1.1 Flash197K$1.50$17.50VisionAug 2026Qwen3.8 FlashLatest fast multimodal model of the Qwen3.8 line: 1M context, t…1M$0.15$0.47VisionReasoningTools / functionsAug 2026Gemini 3.5 TranscribedeprecatedGemini 3.5 Transcribe131K--VisionTools / functionsAug 2026+1GLM-5.3 Flash (1M)Multimodal Flash on a new 320B MoE base (18B activated, hybrid…1M$0.15$0.50VisionReasoningTools / functionsAug 2026GLM 5.3 Flash (Vision)First natively-multimodal model of the GLM-5 line: a 320B MoE (…1M$0.15$0.50VisionReasoningTools / functionsAug 2026DeepSeek V4 Flash Vision (Exp)HOTExperimental vision variant of V4 Flash with 1M context, releas…1M$0.44$1.32VisionReasoningTools / functionsAug 2026Tencent: Hy-MT2-30B-A3BHy-MT2-30B-A3B is Tencent's flagship translation model in the H…8K$0.07$0.30Web searchAug 2026Tencent: Hy-MT2-1.8BHy-MT2-1.8B is a compact 1.8B-parameter translation model from…8K$0.04$0.18Web searchAug 2026Ox AlphadeprecatedOx Alpha is a reasoning model designed for coding, sustained ag…1MFreeFreeVisionReasoningTools / functionsWeb searchAug 2026Tencent: Hy-MT2-7BHy-MT2-7B is a 7B-parameter translation model from Tencent. It…8K$0.07$0.30Web searchAug 2026zai-glm-5Official Z.ai GLM 5.3 model1M$1.40$4.40ReasoningTools / functionsAug 2026Z.ai GLM 5.3Official Z.ai GLM 5.3 model1M$1.40$4.40ReasoningTools / functionsAug 2026+1Qwen3.8 27BOpen-weights 27B dense vision-language model of the Qwen3.8 lin…1M$0.50$3.00VisionReasoningTools / functionsAug 2026+3GLM-5.3 (1M)Z.ai 1M-context flagship, post-trained on the GLM-5.2 base for…1M$1.40$4.40ReasoningTools / functionsAug 2026GLM 5.3 FP8Zai Org chat model. https://huggingface.co/api/models/zai-org/G…1M--Aug 2026GLM 5.3 FastFast serving path for GLM 5.3: same model and quality, lower la…1M$2.10$6.60ReasoningTools / functionsAug 2026GLM 5.3Z.ai flagship, post-trained on the GLM-5.2 base for frontier co…1M$1.40$4.40ReasoningTools / functionsAug 2026Gemini 3.7 Flash Video UnderstandingdeprecatedGemini 3.7 Flash Video Understanding EAP1.1M$0.75$3.75VisionReasoningTools / functionsWeb searchAug 2026Dots Studio: Dots3-Note Preview (free)Dots3-Note Preview is an open-weight mixture-of-experts model f…512KFreeFreeVisionReasoningTools / functionsWeb searchAug 2026Gemini 3.7 FlashHOTGemini 3.7 Flash1.1M$0.75$3.75VisionReasoningTools / functionsWeb searchAug 2026Qwen3.8 2.4T-A95B (Vision)Open-weights release of the Qwen3.8 flagship: 2.4T sparse MoE w…262K$2.00$6.00VisionReasoningTools / functionsAug 2026Qwen3.8 2.4T-A95BOpen-weights release of the Qwen3.8 flagship: 2.4T sparse MoE,…1M$2.00$6.00ReasoningTools / functionsAug 2026Grok 4.6xAI's August 2026 flagship for coding, agentic tasks, and knowl…500K$2.00$6.00VisionReasoningTools / functionsWeb searchAug 2026+2DeepSeek V4 Pro (0813)HOTPremium reasoning model with 1M context, released GA by DeepSee…1M$1.32$3.96ReasoningTools / functionsAug 2026ByteDance Seed: Seed-2.0-CodeSeed 2.0 Code is a model from ByteDance Seed optimized for agen…262K$0.50$3.00VisionReasoningTools / functionsWeb searchAug 2026ByteDance Seed: Seed 2.1 TurboSeed 2.1 Turbo is a multimodal model from ByteDance Seed for co…262K$0.50$2.50VisionReasoningTools / functionsWeb searchAug 2026Sakana: NamazudeprecatedSakana Namazu is a Japanese-specialized reasoning model from Sa…262K$0.95$4.00VisionReasoningTools / functionsWeb searchAug 2026NVIDIA: Nemotron 3.5 LightningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts mod…262K$0.07$0.20ReasoningTools / functionsWeb searchAug 2026NVIDIA Nemotron 3.5 Lightning 30B A3BNVIDIA hybrid Mamba-Transformer MoE (30B params, 3B active) wit…262K$0.05$0.20ReasoningTools / functionsAug 2026Nemotron 3.5 Lightning 30BFastest Nemotron MoE (30B, 3B active), 1M context, reasoning an…1MFreeFreeReasoningTools / functionsAug 2026LiquidAI: LFM2.5-2.6BLFM2.5-2.6B is a compact reasoning model from Liquid AI. It is…128K$0.35$0.50ReasoningTools / functionsWeb searchAug 2026Upstage: Solar Pro 4Solar Pro 4 is Upstage's cost-efficient large language model, f…524K$0.15$0.60ReasoningTools / functionsWeb searchAug 2026Meta: Muse Glimmer 30BMuse Glimmer 30B is a dense, open-weight multimodal model from…131K$0.30$1.20VisionReasoningTools / functionsWeb searchAug 2026inclusionAI: Ling 3.0 Tiny (free)deprecatedLing 3.0 Tiny is a mixture-of-experts model from InclusionAI, w…262KFreeFreeReasoningTools / functionsWeb searchAug 2026Meta: Muse Spark 1.2 ContributorMuse Spark 1.2 contributor tier is a reasoning model from Meta…1M$0.10$0.20VisionReasoningTools / functionsWeb searchAug 2026Meta: Muse Spark 1.2Muse Spark 1.2 is a reasoning model from Meta, designed for com…1M$1.25$4.25VisionReasoningTools / functionsWeb searchAug 2026Sakana Namazu v1.0Japanese-specialized LLM built on Moonshot AI's Kimi K2.6 and a…262K$0.95$4.00VisionReasoningTools / functionsWeb searchAug 2026Sakana NamazuJapanese-specialized LLM with built-in web search and code exec…262K$0.95$4.00VisionReasoningTools / functionsWeb searchAug 2026+2DeepSeek V4 Flash (0731)HOTFast general-purpose model with 1M context, re-post-trained by…1M$0.44$1.32ReasoningTools / functionsJul 2026Thinking Machines: Inkling SmallInkling Small is an open-weight multimodal mixture-of-experts m…524K$0.45$1.20VisionReasoningTools / functionsWeb searchJul 2026Gemini Robotics-ER 2 PreviewGemini Robotics-ER 2 Preview197K$1.00$5.00VisionReasoningTools / functionsWeb searchJul 2026Riva Translate 4B v2Translation-specialized model (37 languages, few-shot prompting…8KFreeFreeJul 2026Claude Opus 5 (Fast)deprecatedFast-mode variant of Opus 5 - identical capabilities with highe…1M$10.00$50.00VisionReasoningTools / functionsWeb searchJul 2026Claude Opus 5Previous Opus model, a step-change improvement over Opus 4.8 fo…1M$5.00$25.00VisionReasoningTools / functionsWeb searchJul 2026inclusionAI: Ling 3.0 Flash*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE)…262K$0.02$0.06ReasoningTools / functionsWeb searchJul 2026Sakana Fugu Ultra v1.1Multi-agent conductor system routing 1-3 expert agents for comp…1M$5.00$30.00VisionReasoningTools / functionsWeb searchJul 2026Sakana Fugu CyberOrchestrator specialized for cybersecurity reasoning: security…1M$6.00$36.00VisionReasoningTools / functionsWeb searchJul 2026Poolside: Laguna S 2.1Laguna S 2.1 is the latest coding agent model from Poolside. La…1M$0.09$0.18ReasoningTools / functionsWeb searchJul 2026Gemini 3.6 FlashGemini 3.6 Flash1.1M$0.75$3.75VisionReasoningTools / functionsWeb searchJul 2026Gemini 3.5 Flash-LiteHOTGemini 3.5 Flash Lite1.1M$0.30$2.50VisionReasoningTools / functionsWeb searchJul 2026Meituan: LongCat 2.0LongCat 2.0 is a sparse mixture-of-experts language model from…1M$0.30$1.20ReasoningTools / functionsWeb searchJul 2026Ising Calibration 1.5 31BNVIDIA quantum-calibration VLM, preview (domain-specific, not f…131KFreeFreeVisionJul 2026Qwen3.8 Max (Vision)Alibaba flagship Qwen3.8 tier, available outside Alibaba infras…262K$2.00$6.00VisionReasoningTools / functionsJul 2026Qwen3.8 MaxFlagship 2.4T-parameter sparse MoE multimodal model with 1M con…1M$2.00$6.00VisionReasoningTools / functionsJul 2026Kimi K3 Spot (Vision)Open-weights model served on Fireworks AI.1M--VisionTools / functionsJul 2026Thinking Machines: InklingInkling is an open-weight multimodal mixture-of-experts model f…524K$1.00$4.05VisionReasoningTools / functionsWeb searchJul 2026Auto Router (Beta)The experimental version of our Auto Router where we test new i…2M--VisionReasoningTools / functionsWeb searchImage outputJul 2026Kimi K3 Fast (Vision)Fast serving path for Kimi K3: same model and quality, lower la…1M$4.50$22.50VisionReasoningTools / functionsJul 2026+3Kimi K3Previous-generation flagship (2.8T parameters), native multimod…1M$3.00$15.00VisionReasoningTools / functionsJul 2026Qwen3.7 FlashLatest fast multimodal model with 1M context, thinking (on by d…1M$0.03$0.13VisionReasoningTools / functionsJul 2026Ternary Bonsai 27BPrism Ml chat model. https://huggingface.co/api/models/prism-ml…262K--VisionJul 2026Pyroworks · Intent Es C9EC41deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent Es 6A34F8deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent Es 3CD022deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent En VERIFY1deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent En C9EC41deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent En BC8D96deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent En 6A34F8deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent En 3CD022deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent De C9EC41deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent De 6A34F8deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Pyroworks · Intent De 3CD022deprecatedFine-tuned adapter served on Fireworks AI.---Jul 2026Kwaipilot: KAT-Coder-Pro V2.5deprecatedKAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model tha…262K$0.74$2.96Tools / functionsWeb searchJul 2026Kwaipilot: KAT-Coder-Air V2.5deprecatedKAT-Coder-Air V2.5 is a flagship-level Agentic Coding model tha…256K$0.15$0.60Tools / functionsWeb searchJul 2026OpenAI: GPT-5.6 Terra ProGPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra…1.1M$2.00$12.00VisionReasoningTools / functionsWeb searchJul 2026OpenAI: GPT-5.6 Sol ProGPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, se…1.1M$4.00$20.00VisionReasoningTools / functionsWeb searchJul 2026OpenAI: GPT-5.6 Luna ProGPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna,…1.1M$0.20$1.20VisionReasoningTools / functionsWeb searchJul 2026Meta: Muse Spark 1.1Muse Spark 1.1 is a multimodal reasoning model from Meta, built…1M$1.25$4.25VisionReasoningTools / functionsWeb searchJul 2026GPT-5.6 TerraBalanced model for efficient, high-volume everyday work. Compet…1.1M$2.00$12.00VisionReasoningTools / functionsWeb searchImage outputJul 2026GPT-5.6 SolFlagship GPT-5.6 tier, for agentic coding, science, and cyberse…1.1M$4.00$20.00VisionReasoningTools / functionsWeb searchImage outputJul 2026GPT-5.6 LunaFastest, most affordable GPT-5.6 model for high-volume work. St…1.1M$0.20$1.20VisionReasoningTools / functionsWeb searchImage outputJul 2026Grok 4.5HOTxAI's July 2026 flagship with frontier performance on coding, k…500K$2.00$6.00VisionReasoningTools / functionsWeb searchJul 2026Muse Image 1.0Meta's image generation model: generates and edits images from…---VisionImage outputJul 2026AionLabs: Aion-3.0-MiniAion-3.0 Mini is a multi-model roleplaying and storytelling sys…131K$0.70$1.40ReasoningTools / functionsWeb searchJul 2026AionLabs: Aion-3.0Aion-3.0 is a multi-model roleplaying and storytelling system f…131K$3.00$6.00ReasoningTools / functionsWeb searchJul 2026Tencent: Hy3Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (…262K$0.13$0.53ReasoningTools / functionsWeb searchJul 2026Poolside: Laguna XS 2.1Laguna XS 2.1 is the latest coding agent model in the 33B-A3B c…262K$0.06$0.12ReasoningTools / functionsWeb searchJul 2026Nano Banana 2 LiteGemini 3.1 Flash Lite Image.131K$0.25$1.50VisionReasoningTools / functionsWeb searchImage outputJun 2026Leanstral 1.5A mid & post-trained version of mistral small 4 for Lean (26061…262K--VisionReasoningTools / functionsJun 2026labs-leanstral-1-5A mid & post-trained version of mistral small 4 for Lean (26061…262K--VisionReasoningTools / functionsJun 2026Gemini Omni Flash Preview (video)Gemini Omni Flash Preview197K$1.50$17.50VisionJun 2026Claude Sonnet 5HOTPrevious Sonnet model, with large gains in coding and agentic t…1M$2.00$10.00VisionTools / functionsWeb searchJun 2026Qwen3.6 35B A3B LoraQwen chat model.262K--VisionJun 2026Qwen3.5 2B LoraQwen chat model.262K--VisionJun 2026Nex AGI: Nex-N2-MinideprecatedNex-N2-Mini is an open-source agentic mixture-of-experts model…262K$0.03$0.10VisionReasoningTools / functionsWeb searchJun 2026Sakana FuguFast orchestration model routing tasks across a swappable pool…1M--VisionReasoningTools / functionsWeb searchJun 2026Cohere: North Mini Code (free)North Mini Code is Cohere's first agentic coding model and the…256KFreeFreeReasoningTools / functionsWeb searchJun 2026Z.ai GLM 5.2Official Z.ai GLM 5.2 model1M$1.40$4.40ReasoningTools / functionsJun 2026+3GLM-5.2 (1M)Z.ai 1M-context flagship (744B MoE, 40B activated). Agentic cod…1M$1.40$4.40ReasoningTools / functionsJun 2026GLM 5.2 FP8Zai Org chat model. https://huggingface.co/api/models/zai-org/G…1M--Jun 2026GLM 5.2 FastdeprecatedFast serving path for GLM 5.2: same model and quality, lower la…1M$2.10$6.60Tools / functionsJun 2026GLM 5.2deprecatedZ.ai flagship with 1M-token context and multi-effort coding for…1M$1.40$4.40Tools / functionsJun 2026Sakana Fugu Ultra v1.0Multi-agent conductor system routing 1-3 expert agents for comp…1M$5.00$30.00VisionReasoningTools / functionsWeb searchJun 2026Sakana Fugu UltraMulti-agent conductor system routing expert agents for complex,…1M$5.00$30.00VisionReasoningTools / functionsWeb searchJun 2026OpenRouter: FusionFusion turns your prompt into a small multi-model deliberation.…1M--Web searchJun 2026Kimi K2.7 Code HighspeedHigh-speed code variant with ~180 tok/s output (up to 260 in sh…262K$1.90$8.00VisionReasoningTools / functionsJun 2026Kimi K2.7 Code Fast (Vision)deprecatedFast serving path for Kimi K2.7 Code: same model and quality, l…262K$1.90$8.00VisionTools / functionsJun 2026Kimi K2.7 Code (Vision)deprecatedCoding-focused agentic model built on Kimi K2.6, with better en…262K$0.95$4.00VisionTools / functionsJun 2026+1Kimi K2.7 CodeCode-focused multimodal model (text, image, video inputs) with…262K$0.95$4.00VisionReasoningTools / functionsJun 2026DiffusionGemma 26BExperimental diffusion language model. CAUTION: prone to hangin…250KFreeFreeVisionReasoningTools / functionsJun 2026Qwen3.7 Plus (Vision)deprecatedAlibaba flagship closed model, available outside Alibaba infras…-$0.40$1.60VisionTools / functionsJun 2026

CO

North Mini CodeCompact agentic coding MoE (30B total, 3B active, Apache 2.0) f…436K--ReasoningTools / functionsJun 2026Claude Fable 5Previous Fable-tier model for the most demanding reasoning and…1M$10.00$50.00VisionReasoningTools / functionsWeb searchJun 2026Nex AGI: Nex-N2-ProdeprecatedNex-N2-Pro is an agentic mixture-of-experts model from Nex AGI,…262K$0.25$1.00VisionReasoningWeb searchJun 2026NVIDIA: Nemotron 3.5 Content SafetyNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter mu…131K$0.20$0.20VisionReasoningWeb searchJun 2026NVIDIA: Nemotron 3 UltraHOTNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orche…262K$0.60$2.40ReasoningTools / functionsWeb searchJun 2026NVIDIA Nemotron 3 Ultra NVFP4NVIDIA frontier-scale hybrid LatentMoE (550B params, 55B active…262K$0.60$2.40ReasoningTools / functionsJun 2026Llama 4 Maverick 17B 128E Instruct Nvfp4Meta chat model. https://huggingface.co/api/models/RedHatAI/Lla…1M--VisionJun 2026GLM 4.7 FP4Zai Org chat model.203K--Jun 2026Qwen3.7 PlusMultimodal agent model with 1M context, native thinking, and vi…1M$0.40$1.60VisionReasoningTools / functionsJun 2026+2MiniMax M3Flagship: frontier coding and agentic reasoning, natively multi…1M$0.30$1.20VisionReasoningTools / functionsMay 2026StepFun: Step 3.7 FlashStep 3.7 Flash is StepFun's latest high-efficiency multimodal M…262K$0.20$1.15VisionReasoningTools / functionsWeb searchMay 2026Nano Banana ProGemini 3 Pro Image164K$2.00$12.00VisionReasoningTools / functionsWeb searchImage outputMay 2026Nano Banana 2Gemini 3.1 Flash Image.131K$0.50$3.00VisionReasoningTools / functionsWeb searchImage outputMay 2026Claude Opus 4.8Previous most capable Opus-tier model for complex reasoning and…1M$5.00$25.00VisionTools / functionsWeb searchMay 2026Anthropic: Claude Opus 4.8 (Fast)deprecatedFast-mode variant of Opus 4.8 - identical capabilities with hig…1M$10.00$50.00VisionTools / functionsWeb searchMay 2026Qwen3.7 MaxFlagship agent model with native extended thinking and 1M conte…1M$2.50$7.50ReasoningTools / functionsMay 2026Grok Build 0.1xAI fast coding model with reasoning, function calling, and str…256K$1.00$2.00VisionReasoningTools / functionsWeb searchMay 2026

CO

Command A PlusCohere flagship MoE (218B total, 25B active, Apache 2.0). Agent…436K--VisionReasoningTools / functionsMay 2026Llama 4 Scout 17B 16E Instruct Fp8 LoraMeta chat model.10M--VisionMay 2026Gemini 3.5 FlashGemini 3.5 Flash1.1M$0.75$3.75VisionReasoningTools / functionsWeb searchMay 2026Antigravity Agent Preview (2026-05)Preview release of Antigravity Agent (05-2026)1.1M$0.75$3.75VisionReasoningMay 2026Gemma 4 31B It LoraGoogle chat model. https://huggingface.co/api/models/google/gem…262K--VisionMay 2026Gemma 3 27B It LoraGoogle chat model.---VisionMay 2026Perceptron: Perceptron Mk1Perceptron Mk1 (Mark One) is Perceptron's highest-quality visio…33K$0.15$1.50VisionReasoningWeb searchMay 2026inclusionAI: Ring-2.6-1TdeprecatedRing-2.6-1T is a 1T-parameter-scale thinking model with 63B act…262K$0.08$0.63ReasoningTools / functionsWeb searchMay 2026Mixtral 8x7B Instruct V0.1 FP8 LoraMistral AI chat model.33K--May 2026Gemma 3 270M It LoraGoogle chat model.33K--May 2026Gemini 3.1 Flash-LiteHOTGemini 3.1 Flash Lite1.1M$0.25$1.50VisionReasoningTools / functionsWeb searchMay 2026Llama 3.3 70B Instruct FP8 LoraMeta chat model.131K--May 2026ChatGPT Instant400K$5.00$30.00VisionTools / functionsWeb searchImage outputMay 2026IBM: Granite 4.1 8BdeprecatedGranite 4.1 8B is a dense, decoder-only 8-billion-parameter lan…131K$0.05$0.10Tools / functionsWeb searchApr 2026Poolside: Laguna XS.2deprecatedLaguna XS.2 is the second-generation model in the XS size class…262K$0.10$0.20ReasoningTools / functionsWeb searchApr 2026Poolside: Laguna M.1deprecatedLaguna M.1 is the flagship coding agent model from Poolside, op…262K$0.20$0.40ReasoningTools / functionsWeb searchApr 2026Owl AlphaOwl Alpha is a high-performance foundation model designed for a…1MFreeFreeTools / functionsWeb searchApr 2026NVIDIA: Nemotron 3 Nano Omni (free)NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model…256KFreeFreeVisionReasoningTools / functionsWeb searchApr 2026Nemotron 3 Nano Omni 30B A3b Reasoning Fp8Nvidia chat model.131K--VisionApr 2026Mistral: Mistral Medium 3.5Official mistral-medium-latest Mistral model262K$1.50$7.50VisionReasoningTools / functionsApr 2026mistral-vibe-cli-with-toolsOfficial mistral-medium-latest Mistral model262K$1.50$7.50VisionReasoningTools / functionsApr 2026mistral-mediumOfficial mistral-medium-latest Mistral model262K$1.50$7.50VisionReasoningTools / functionsApr 2026Mistral Medium 3.5deprecatedMistral frontier-class multimodal model with adjustable reasoni…262KFreeFreeVisionReasoningTools / functionsApr 2026Mistral Medium (2604)Official mistral-medium-latest Mistral model262K$1.50$7.50VisionReasoningTools / functionsApr 2026Qwen3.6 Max PreviewdeprecatedQwen3.6 Max preview (never GA; superseded by Qwen3.7 Max). 256K…262K$1.30$7.80ReasoningTools / functionsApr 2026Qwen3.6 FlashFast, cost-effective multimodal model with 1M context, near-fla…1M$0.25$1.50VisionReasoningTools / functionsApr 2026Qwen3.6 35B-A3BOpen 35B-A3B MoE multimodal with thinking. 256K context.262K$0.38$2.25VisionReasoningTools / functionsApr 2026Qwen3.6 27BOpen 27B dense multimodal with thinking. 256K context.262K$0.60$3.60VisionReasoningTools / functionsApr 2026Spot DeepSeek V4 FlashOpen-weights model served on Fireworks AI.1M--Tools / functionsApr 2026inclusionAI: Ling-2.6-1TdeprecatedLing-2.6-1T is an instant (instruct) model from inclusionAI and…262K$0.08$0.63Tools / functionsWeb searchApr 2026GPT-5.5 ProMost capable model for complex tasks. Uses more compute for sma…1.1M$30.00$180.00VisionReasoningTools / functionsWeb searchImage outputApr 2026GPT-5.5New baseline for complex production workflows. Stronger task ex…1.1M$5.00$30.00VisionReasoningTools / functionsWeb searchImage outputApr 2026Xiaomi: MiMo-V2.5-ProMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong per…1.1M$0.48$1.80ReasoningTools / functionsWeb searchApr 2026Xiaomi: MiMo-V2.5MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pr…1.1M$0.40$2.00VisionReasoningTools / functionsWeb searchApr 2026Tencent: Hy3 previewHy3 preview is a high-efficiency Mixture-of-Experts model from…262K$0.18$0.60ReasoningTools / functionsWeb searchApr 2026Qwen3.6 35B A3b Fp8Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3.6…262K--VisionApr 2026Pareto Code RouterThe Pareto Router maintains a tiered shortlist of strong coding…2M--ReasoningTools / functionsWeb searchApr 2026OpenAI: GPT-5.4 Image 2deprecatedGPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-t…272K$8.00$15.00VisionReasoningWeb searchImage outputApr 2026inclusionAI: Ling-2.6-flashdeprecatedLing-2.6-flash is an instant (instruct) model from inclusionAI…262K$0.01$0.03Tools / functionsWeb searchApr 2026Gemma 4 E2B-itGoogle chat model. https://huggingface.co/api/models/google/gem…131K--VisionApr 2026Deep Research Preview (2026-04)Preview release (April 21th, 2026) of Deep Research197K$1.25$10.00VisionReasoningApr 2026Deep Research Max Preview (2026-04)Preview release (April 21st, 2026) of Deep Research Max197K$1.25$10.00VisionReasoningApr 2026Kimi K2.6Native multimodal flagship (text, image, video inputs) with thi…262K$0.95$4.00VisionTools / functionsApr 2026Kimi K2.6 Fast (Vision)deprecatedFast serving path for Kimi K2.6: same model and quality, lower…262K$2.00$8.00VisionTools / functionsApr 2026Kimi K2.6 (Vision)deprecatedMoonshot AI native-multimodal agentic model tuned for long-hori…262K$0.95$4.00VisionTools / functionsApr 2026Grok 4.3xAI's latest flagship model with reasoning and a 1M token conte…1M$1.25$2.50VisionReasoningTools / functionsWeb searchApr 2026Gemma 4 E4B-itGoogle chat model. https://huggingface.co/google/gemma-4-E4B-it131K--VisionApr 2026Claude Opus 4.7Previous most capable model for complex reasoning and agentic c…1M$5.00$25.00VisionTools / functionsWeb searchApr 2026Anthropic: Claude Opus 4.7 (Fast)deprecatedFast-mode variant of Opus 4.7 - identical capabilities with hig…1M$30.00$150.00VisionTools / functionsWeb searchApr 2026Gemini 3.1 Flash TTS PreviewGemini 3.1 Flash TTS Preview25K$1.00-VisionAudio outputApr 2026Ising Calibration 1 35BdeprecatedNVIDIA quantum-calibration VLM (domain-specific, not for genera…262KFreeFreeVisionReasoningApr 2026Gemini Robotics-ER 1.6 PreviewdeprecatedGemini Robotics-ER 1.6 Preview197K$1.00$5.00VisionReasoningTools / functionsApr 2026MiniMax M2.7deprecatedMiniMax MoE built for complex agent harnesses and elaborate pro…197K$0.30$1.20Tools / functionsApr 2026Nvidia Nemotron 3 Super 120B A12b Bf16Nvidia chat model. https://huggingface.co/api/models/nvidia/NVI…262K--Apr 2026GLM-5.1Z.ai flagship (744B MoE, 40B activated). Post-training upgrade…205K$1.40$4.40ReasoningTools / functionsApr 2026Qwen3.6 PlusPrevious Plus tier, superseded by Qwen3.7 Plus. 1M context, thi…1M$0.50$3.00VisionReasoningTools / functionsApr 2026+1Gemma 4 31B ITHOTGemma 4 31B IT295KFreeFreeVisionReasoningTools / functionsApr 2026Gemma 4 31BdeprecatedGoogle Gemma 4 31B instruction-tuned, text+image input. Served…262K$0.25$0.65VisionTools / functionsApr 2026Gemma 4 26B A4B ITGemma 4 26B A4B IT295KFreeFreeVisionReasoningTools / functionsApr 2026GLM-5V TurboFirst multimodal GLM-5 model. Vision-based coding agent with im…205K$1.20$4.00VisionReasoningTools / functionsApr 2026Arcee AI: Trinity Large ThinkingdeprecatedTrinity Large Thinking is a powerful open source reasoning mode…262K$0.25$0.80ReasoningTools / functionsWeb searchApr 2026SpaceXAI: Grok 4.20Grok 4.20 is a reasoning model from SpaceXAI with industry-lead…2M$1.25$2.50VisionReasoningTools / functionsWeb searchMar 2026Holo3 35B A3bHcompany chat model. https://huggingface.co/api/models/Hcompany…262K--Mar 2026Google: Lyria 3 Pro PreviewdeprecatedFull-length songs are priced at $0.08 per song. Lyria 3 is Goog…1MFreeFreeVisionWeb searchAudio outputMar 2026Google: Lyria 3 Clip Previewdeprecated30 second duration clips are priced at $0.04 per clip. Lyria 3…1MFreeFreeVisionWeb searchAudio outputMar 2026routers · glm 5.1 FastdeprecatedOpen-weights model served on Fireworks AI.203K--Tools / functionsMar 2026Kwaipilot: KAT-Coder-Pro V2deprecatedKAT-Coder-Pro V2 is the latest high-performance model in KwaiKA…262K$0.30$1.20Tools / functionsWeb searchMar 2026GLM 5.1deprecatedZ.ai 754B-parameter MoE built for agentic engineering, with str…203K$1.40$4.40Tools / functionsMar 2026Qwen3 30B A3B Instruct 2507 LoraQwen chat model.262K--Mar 2026DeepSeek V3.1Deepseek model via OpenAI-Compatible API on AWS Bedrock Mantle131K$0.60$1.70Tools / functionsMar 2026Reka EdgeReka Edge is an extremely efficient 7B multimodal vision-langua…16K$0.10$0.10VisionTools / functionsWeb searchMar 2026Qwen3 8B LoraQwen chat model.41K--Mar 2026MiniMax M2.7 (Highspeed)Faster M2.7 variant at ~100 t/s. 200K context, 131K max output.205K$0.60$2.40ReasoningTools / functionsMar 2026MiniMax M2.7Recursive self-improvement and agentic capabilities. 200K conte…205K$0.30$1.20ReasoningTools / functionsMar 2026GPT-5.4 NanoCheapest GPT-5.4-class model for simple high-volume tasks like…400K$0.20$1.25VisionReasoningTools / functionsWeb searchImage outputMar 2026GPT-5.4 MiniHOTStrongest mini model for coding, computer use, and subagents. G…400K$0.75$4.50VisionReasoningTools / functionsWeb searchImage outputMar 2026Qwen3.5 122B A10b Fp8Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3.5…262K--VisionMar 2026mistral-vibe-cli-fastMistral Small 4.262K$0.15$0.60VisionReasoningTools / functionsMar 2026Mistral Small (2603)Mistral Small 4.262K$0.15$0.60VisionReasoningTools / functionsMar 2026Leanstral (2603)A mid & post-trained version of mistral small 4 for Lean197K--VisionTools / functionsMar 2026GLM-5 TurboSpeed-optimized GLM-5 variant for agent workflows. Enhanced too…205K$1.20$4.00ReasoningTools / functionsMar 2026Deepseek OCR 2Deepseek chat model. https://huggingface.co/api/models/deepseek…8K--VisionMar 2026NVIDIA: Nemotron 3 SuperNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE mod…1M$0.30$2.40ReasoningTools / functionsWeb searchMar 2026Nvidia Nemotron 3 Super 120B A12b Fp8Nvidia chat model. https://huggingface.co/api/models/nvidia/NVI…262K--Mar 2026Qwen: Qwen3.5-9BQwen3.5-9B is a multimodal foundation model from the Qwen3.5 fa…262K$0.17$0.25VisionReasoningTools / functionsWeb searchMar 2026ByteDance Seed: Seed-2.0-LiteSeed-2.0-Lite is a versatile, cost‑efficient enterprise workhor…262K$0.25$2.00VisionReasoningTools / functionsWeb searchMar 2026Grok 4.20 ReasoningxAI flagship reasoning model with a 1M token context window. De…1M$1.25$2.50VisionReasoningTools / functionsWeb searchMar 2026Grok 4.20 Multi-AgentMulti-agent model that runs specialized agents in parallel for…1M$1.25$2.50VisionReasoningWeb searchMar 2026Grok 4.20xAI flagship model with a 1M token context window. Non-reasonin…1M$1.25$2.50VisionTools / functionsWeb searchMar 2026Qwen3.5 9B Fp8Qwen chat model. https://huggingface.co/api/models/togethercomp…262K--VisionMar 2026GPT-5.4 ProMost capable model for complex tasks. Uses more compute for sma…1.1M$30.00$180.00VisionReasoningTools / functionsWeb searchImage outputMar 2026GPT-5.4Most capable and efficient frontier model for professional work…1.1M$2.50$15.00VisionReasoningTools / functionsWeb searchImage outputMar 2026Inception: Mercury 2Mercury 2 is an extremely fast reasoning LLM, and the first rea…128K$0.25$0.75ReasoningTools / functionsWeb searchMar 2026OpenAI: GPT-5.3 ChatdeprecatedGPT-5.3 Chat is an update to ChatGPT's most-used model that mak…128K$1.75$14.00VisionTools / functionsWeb searchMar 2026GPT-5.3 InstantdeprecatedGPT-5.3 Instant model, previously powering ChatGPT.128K$1.75$14.00VisionTools / functionsWeb searchImage outputMar 2026Glm 4.7 Fp8Zai Org chat model. https://huggingface.co/api/models/zai-org/G…203K--Mar 2026Gemini 3.1 Flash-Lite PreviewGemini 3.1 Flash Lite Preview1.1M$0.25$1.50VisionReasoningTools / functionsWeb searchMar 2026Nano Banana 2 PreviewGemini 3.1 Flash Image Preview.131K$0.50$3.00VisionReasoningTools / functionsWeb searchImage outputFeb 2026ByteDance Seed: Seed-2.0-MiniSeed-2.0-mini targets latency-sensitive, high-concurrency, and…262K$0.10$0.40VisionReasoningTools / functionsWeb searchFeb 2026Qwen3.5 35B-A3BOpen 35B-A3B MoE multimodal with thinking. 256K context.262K$0.25$2.00VisionReasoningTools / functionsFeb 2026Qwen3.5 27BOpen 27B dense multimodal with thinking. 256K context.262K$0.30$2.40VisionReasoningTools / functionsFeb 2026Qwen3.5 122B-A10BOpen 122B-A10B MoE multimodal with thinking. 256K context.262K$0.40$3.20VisionReasoningTools / functionsFeb 2026Qwen: Qwen3.5-FlashThe Qwen3.5 native vision-language Flash models are built on a…1M$0.07$0.26VisionReasoningTools / functionsWeb searchFeb 2026LiquidAI: LFM2-24B-A2BdeprecatedLFM2-24B-A2B is the largest model in the LFM2 family of hybrid…128K$0.03$0.12Web searchFeb 2026GPT Audio 1.5Best voice model for audio in, audio out with Chat Completions.…128K$2.50$10.00Audio outputFeb 2026Qwen3.5 FlashFormer Flash tier, superseded by Qwen3.6/3.7 Flash. 1M context,…1M$0.10$0.40VisionReasoningTools / functionsFeb 2026AionLabs: Aion-2.0Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive…131K$0.80$1.60ReasoningTools / functionsWeb searchFeb 2026Gemini 3.1 Pro Preview (Custom Tools)Gemini 3.1 Pro Preview optimized for custom tool usage1.1M$2.00$12.00VisionReasoningTools / functionsWeb searchFeb 2026Gemini 3.1 Pro PreviewHOTGemini 3.1 Pro Preview1.1M$2.00$12.00VisionReasoningTools / functionsWeb searchFeb 2026

CO

Tiny Aya WaterTiny Aya (3.35B) region-specialized for European and Asia-Pacif…8K--Feb 2026

CO

Tiny Aya GlobalTiny multilingual research model (3.35B), best balance across 7…8K--Feb 2026

CO

Tiny Aya FireTiny Aya (3.35B) region-specialized for South Asian languages.…8K--Feb 2026

CO

Tiny Aya EarthTiny Aya (3.35B) region-specialized for West Asian and African…8K--Feb 2026Claude Sonnet 4.6Best combination of speed and intelligence for everyday tasks1M$3.00$15.00VisionTools / functionsWeb searchFeb 2026Qwen3.5 397B-A17BOpen 397B-A17B MoE multimodal with thinking. 256K context.262K$0.60$3.60VisionReasoningTools / functionsFeb 2026Qwen: Qwen3.5 Plus 2026-02-15The Qwen3.5 native vision-language series Plus models are built…1M$0.26$1.56VisionReasoningTools / functionsWeb searchFeb 2026Qwen3.5 PlusFormer Plus tier, superseded by Qwen3.6/3.7 Plus. 1M context, t…1M$0.40$2.40VisionReasoningTools / functionsFeb 2026MiniMax M2.5 FP4MiniMaxAI chat model.8K--Feb 2026MiniMax M2.5 (Highspeed)Faster M2.5 variant at ~100 t/s. 200K context, 131K max output.205K$0.60$2.40ReasoningTools / functionsFeb 2026MiniMax M2.5Strong coding and reasoning, best value. 200K context, 131K max…205K$0.30$1.20ReasoningTools / functionsFeb 2026GLM 5 Fp4Zai Org chat model. https://huggingface.co/api/models/togetherc…203K--Feb 2026GLM-5Z.ai flagship foundation model (744B MoE, 40B activated). Desig…205K$1.00$3.20ReasoningTools / functionsFeb 2026Qwen: Qwen3 Max ThinkingdeprecatedQwen3-Max-Thinking is the flagship reasoning model in the Qwen3…262K$0.78$3.90ReasoningTools / functionsWeb searchFeb 2026GPT-5.3 CodexdeprecatedMost capable agentic coding model. Combines frontier coding per…400K$1.75$14.00VisionReasoningTools / functionsWeb searchImage outputFeb 2026Claude Opus 4.6Previous most intelligent model for complex agents and coding,…1M$5.00$25.00VisionTools / functionsWeb searchFeb 2026Qwen3 Coder NextBudget agentic coder on the Qwen3-Next architecture. 256K conte…262K$0.30$1.50Tools / functionsFeb 2026GLM-OCR (Vision, OCR)Specialized OCR model for text extraction from images and docum…131K$0.03$0.03VisionFeb 2026Free Models RouterThe simplest way to get free inference. openrouter/free is a ro…200KFreeFreeVisionReasoningTools / functionsWeb searchFeb 2026StepFun: Step 3.5 FlashStep 3.5 Flash is StepFun's most capable open-source foundation…262K$0.10$0.30ReasoningTools / functionsWeb searchJan 2026Upstage: Solar Pro 3deprecatedSolar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) lang…131K$0.15$0.60ReasoningTools / functionsWeb searchJan 2026MiniMax M2-herdeprecatedDialogue-first model for immersive roleplay, character-driven c…66K$0.30$1.20Jan 2026Kimi K2.5 (Vision)deprecatedOpen-weights model served on Fireworks AI.262K--VisionTools / functionsJan 2026Kimi K2.5Supports vision (images/videos), thinking mode, and Agent tasks…262K$0.60$3.00VisionTools / functionsJan 2026MiniMax M2-herDialogue-first model for immersive roleplay, character-driven c…66K$0.30$1.20Tools / functionsJan 2026Writer: Palmyra X5Palmyra X5 is Writer's most advanced model, purpose-built for b…1M$0.60$6.00Web searchJan 2026LiquidAI: LFM2.5-1.2B-Thinking (free)deprecatedLFM2.5-1.2B-Thinking is a lightweight reasoning-focused model o…33KFreeFreeReasoningWeb searchJan 2026LiquidAI: LFM2.5-1.2B-Instruct (free)deprecatedLFM2.5-1.2B-Instruct is a compact, high-performance instruction…33KFreeFreeJan 2026GLM-4.7 FlashXFast GLM-4.7 variant with priority routing and higher concurren…205K$0.07$0.40ReasoningTools / functionsJan 2026GLM-4.7 Flash (Free)Free GLM-4.7 variant. Same model as FlashX but with limited con…205KFreeFreeReasoningTools / functionsJan 2026Z.ai GLM 4.7 (Preview)Z.ai GLM 4.7 (355B) on Cerebras (~1,000 tok/s). Strong agentic…131K$2.25$2.75ReasoningTools / functionsJan 2026ByteDance Seed: Seed 1.6 FlashSeed 1.6 Flash is an ultra-fast multimodal deep thinking model…262K$0.08$0.30VisionReasoningTools / functionsWeb searchDec 2025ByteDance Seed: Seed 1.6Seed 1.6 is a general-purpose model released by the ByteDance S…262K$0.25$2.00VisionReasoningTools / functionsWeb searchDec 2025MiniMax M2.1 (Highspeed)Faster M2.1 variant. 200K context, 131K max output.205K$0.60$2.40ReasoningTools / functionsDec 2025MiniMax M2.1230B params (10B active), multilingual coding. 200K context, 13…205K$0.30$1.20ReasoningTools / functionsDec 2025GLM-4.7Latest-gen GLM model with 200K context. Thinking mode activated…205K$0.60$2.20ReasoningTools / functionsDec 2025Gemini 3 Flash PreviewGemini 3 Flash Preview1.1M$0.50$3.00VisionReasoningTools / functionsWeb searchDec 2025Nvidia Nemotron 3 Nano 30B A3b Bf16Nvidia chat model. https://huggingface.co/api/models/nvidia/NVI…262K--Dec 2025NVIDIA: Nemotron 3 Nano 30B A3BNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model wi…262K$0.06$0.24ReasoningTools / functionsWeb searchDec 2025Riva Translate 4B v1.1deprecatedTranslation-specialized model, 8K context.8KFreeFreeDec 2025OpenAI: GPT-5.2 ChatdeprecatedGPT-5.2 Chat (AKA Instant) is the fast, lightweight member of t…128K$1.75$14.00VisionTools / functionsWeb searchDec 2025GPT-5.2 InstantdeprecatedGPT-5.2 Instant model, previously powering ChatGPT.128K$1.75$14.00VisionTools / functionsWeb searchImage outputDec 2025GPT-5.2 CodexdeprecatedGPT-5.2 optimized for long-horizon, agentic coding tasks in Cod…400K$1.75$14.00VisionReasoningTools / functionsWeb searchImage outputDec 2025Deep Research Pro PreviewDeprecated preview agent; automatically rerouting traffic to de…197K$1.25$10.00VisionReasoningDec 2025AutoGLM PhoneMobile phone automation agent. Understands phone screens via mu…131KFreeFreeVisionDec 2025GPT-5.2 ProSmartest and most trustworthy option for difficult questions. U…400K$21.00$168.00VisionReasoningTools / functionsWeb searchImage outputDec 2025GPT-5.2Most capable model for professional work and long-running agent…400K$1.75$14.00VisionReasoningTools / functionsWeb searchImage outputDec 2025Mistral: Devstral 2 2512Devstral 2 is a state-of-the-art open-source model by Mistral A…262K$0.40$2.00Tools / functionsWeb searchDec 2025Relace: Relace SearchThe relace-search model uses 4-12 `view_file` and `grep` tools…256K$1.00$3.00Tools / functionsWeb searchDec 2025GLM-4.6 V FlashXFast vision GLM-4.6 with priority routing and higher concurrenc…131K$0.04$0.40VisionReasoningTools / functionsDec 2025GLM-4.6 V Flash (Free)Free vision GLM-4.6. Same model as FlashX but with limited conc…131KFreeFreeVisionReasoningTools / functionsDec 2025GLM-4.6 VVision-enabled GLM-4.6 model. Supports image/video/file inputs,…131K$0.30$0.90VisionReasoningTools / functionsDec 2025EssentialAI Rnj-1 InstructEssential AI chat model. https://huggingface.co/api/models/toge…33K--Dec 2025Body Builder (beta)Transform your natural language requests into structured OpenRo…128K--Web searchDec 2025Ministral 8b (2512)Ministral 3 (a.k.a. Tinystral) 8B Instruct.262K$0.15$0.15VisionTools / functionsDec 2025Ministral 3b (2512)Ministral 3 (a.k.a. Tinystral) 3B Instruct.131K$0.10$0.10VisionTools / functionsDec 2025Ministral 3 14B Instruct 2512deprecatedMistralai chat model. https://huggingface.co/api/models/mistral…262K$0.20$0.20Dec 2025Ministral 14b (2512)Ministral 3 (a.k.a. Tinystral) 14B Instruct.262K$0.20$0.20VisionTools / functionsDec 2025Amazon: Nova 2 LiteNova 2 Lite is a fast, cost-effective reasoning model for every…1M$0.30$2.50VisionReasoningTools / functionsWeb searchDec 2025Mistral Large (2512)Release candidate for ml3.262K$0.50$1.50VisionTools / functionsDec 2025DeepSeek: DeepSeek V3.2DeepSeek-V3.2 is a large language model designed to harmonize h…164K$0.26$0.38ReasoningTools / functionsWeb searchDec 2025Arcee AI: Trinity MiniTrinity Mini is a 26B-parameter (3B active) sparse mixture-of-e…131K$0.05$0.15ReasoningTools / functionsWeb searchDec 2025Claude Opus 4.5Previous most intelligent model with advanced reasoning for com…200K$5.00$25.00VisionTools / functionsWeb searchNov 2025AllenAI: Olmo 3 32B ThinkdeprecatedOlmo 3 32B Think is a large-scale, 32-billion-parameter model p…66K$0.15$0.50ReasoningWeb searchNov 2025Nano Banana Pro PreviewGemini 3 Pro Image Preview164K$2.00$12.00VisionReasoningTools / functionsWeb searchImage outputNov 2025Nano Banana ProGemini 3 Pro Image Preview164K$2.00$12.00VisionReasoningTools / functionsWeb searchImage outputNov 2025GPT-5.1 Codex MaxdeprecatedOur most intelligent coding model optimized for long-horizon, a…400K$1.25$10.00VisionReasoningTools / functionsWeb searchImage outputNov 2025GPT-5.1 Codex MinideprecatedSmaller, faster version of GPT-5.1 Codex for efficient coding t…400K$0.25$2.00VisionReasoningTools / functionsWeb searchImage outputNov 2025GPT-5.1 CodexdeprecatedA version of GPT-5.1 optimized for agentic coding tasks in Code…400K$1.25$10.00VisionReasoningTools / functionsWeb searchImage outputNov 2025GPT-5.1HOTThe best model for coding and agentic tasks with configurable r…400K$1.25$10.00VisionReasoningTools / functionsWeb searchImage outputNov 2025Deep Cogito: Cogito v2.1 671BdeprecatedCogito v2.1 671B MoE represents one of the strongest open model…128K$1.25$1.25ReasoningWeb searchNov 2025OpenAI: GPT-5.1 ChatdeprecatedGPT-5.1 Chat (AKA Instant is the fast, lightweight member of th…128K$1.25$10.00VisionReasoningTools / functionsWeb searchNov 2025GPT-5.1 InstantdeprecatedGPT-5.1 Instant with adaptive reasoning. More conversational wi…128K$1.25$10.00VisionReasoningTools / functionsWeb searchImage outputNov 2025Qwen3-VL-235B-A22B-Instruct-FP8Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-V…262K--VisionNov 2025MoonshotAI: Kimi K2 ThinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning…262K$0.60$2.50ReasoningTools / functionsWeb searchNov 2025Amazon: Nova Premier 1.0Amazon Nova Premier is the most capable of Amazon’s multimodal…1M$2.50$12.50VisionTools / functionsWeb searchOct 2025Perplexity: Sonar Pro SearchExclusively available on the OpenRouter API, Sonar Pro's new Pr…200K$3.00$15.00VisionReasoningWeb searchOct 2025Mistral: Voxtral Small 24B 2507Voxtral Small is an enhancement of Mistral Small 3, incorporati…33K$0.10$0.30Tools / functionsWeb searchOct 2025OpenAI: gpt-oss-safeguard-20bgpt-oss-safeguard-20b is a safety reasoning model from OpenAI b…131K$0.08$0.30ReasoningTools / functionsWeb searchOct 2025NVIDIA: Nemotron Nano 12B 2 VL (free)deprecatedNVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multim…128KFreeFreeVisionReasoningTools / functionsWeb searchOct 2025Nemotron Safety Guard 8B v3NVIDIA content-safety classifier (not a chat model).131KFreeFreeOct 2025Medgemma 27B Text ItGoogle chat model. https://huggingface.co/api/models/google/med…131K--Oct 2025Qwen: Qwen3 VL 32B InstructdeprecatedQwen3-VL-32B-Instruct is a large-scale multimodal vision-langua…131K$0.10$0.42VisionTools / functionsWeb searchOct 2025MiniMax M2230B params (10B active), agentic and reasoning. 200K context,…205K$0.30$1.20ReasoningTools / functionsOct 2025IBM: Granite 4.0 MicrodeprecatedGranite-4.0-H-Micro is a 3B parameter from the Granite 4 family…131K$0.02$0.11Web searchOct 2025Microsoft: Phi 4 Mini InstructPhi-4-mini-instruct is a lightweight open model built upon synt…131K$0.08$0.35Web searchOct 2025Qwen3 VL FlashdeprecatedBudget VL tier below Qwen3 VL Plus. 256K context, thinking, vis…262K$0.05$0.40VisionReasoningTools / functionsOct 2025Claude Haiku 4.5Previous Haiku model, with extended thinking and exceptional sp…200K$1.00$5.00VisionTools / functionsWeb searchOct 2025Qwen: Qwen3 VL 8B ThinkingdeprecatedQwen3-VL-8B-Thinking is the reasoning-optimized variant of the…131K$0.18$2.10VisionReasoningTools / functionsWeb searchOct 2025Qwen: Qwen3 VL 8B InstructQwen3-VL-8B-Instruct is a multimodal vision-language model from…262K$0.25$0.75VisionTools / functionsWeb searchOct 2025GPT-5 Search APIUpdated web search model in Chat Completions API. 60% cheaper w…400K$1.25$10.00VisionWeb searchOct 2025NVIDIA: Llama 3.3 Nemotron Super 49B V1.5deprecatedLlama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-c…131K$0.40$0.40ReasoningTools / functionsWeb searchOct 2025QWEN3 Reranker 8BdeprecatedModel served on Fireworks AI.41K--Oct 2025Gemini 2.5 Computer Use Preview 10-2025Gemini 2.5 Computer Use Preview 10-2025197K$1.25$10.00VisionReasoningTools / functionsOct 2025Qwen: Qwen3 VL 30B A3B ThinkingQwen3-VL-30B-A3B-Thinking is a multimodal model that unifies st…262K$0.29$1.00VisionReasoningTools / functionsWeb searchOct 2025Qwen: Qwen3 VL 30B A3B InstructQwen3-VL-30B-A3B-Instruct is a multimodal model that unifies st…262K$0.15$0.60VisionTools / functionsWeb searchOct 2025GPT-5 ProVersion of GPT-5 that uses more compute to produce smarter and…400K$15.00$120.00VisionReasoningTools / functionsWeb searchImage outputOct 2025GPT Audio MinideprecatedCost-efficient audio model. Accepts audio inputs and outputs vi…128K$0.60$2.40Audio outputOct 2025Nano BananaGemini 2.5 Flash Preview Image66K$0.30$2.50VisionImage outputOct 2025GLM-4.6GLM-4.6 model with 200K context, 128K output. Hybrid thinking:…205K$0.60$2.20ReasoningTools / functionsSep 2025Gemma 3 270M ItGoogle chat model. https://huggingface.co/api/models/google/gem…33K--Sep 2025DeepSeek: DeepSeek V3.2 ExpDeepSeek-V3.2-Exp is an experimental large language model relea…164K$0.27$0.41ReasoningTools / functionsWeb searchSep 2025Claude Sonnet 4.5HOTPrevious best combination of speed and intelligence for complex…200K$3.00$15.00VisionTools / functionsWeb searchSep 2025TheDrummer: Cydonia 24B V4.1Uncensored and creative writing model based on Mistral Small 3.…131K$0.30$0.50Web searchSep 2025Relace: Relace Apply 3Relace Apply 3 is a specialized code-patching LLM that merges A…256K$0.85$1.25Web searchSep 2025Google: Gemini 2.5 Flash Lite Preview 09-2025deprecatedGemini 2.5 Flash-Lite is a lightweight reasoning model in the G…1M$0.10$0.40VisionReasoningTools / functionsWeb searchSep 2025Qwen3 Next 80B A3b Instruct Fp8Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-N…---Sep 2025Qwen3 Vl 235b A22b ThinkingdeprecatedAlibaba model (not yet curated).131K$0.40$4.00Tools / functionsSep 2025Qwen3 Vl 235b A22b InstructAlibaba model (not yet curated).131K$0.21$1.90Tools / functionsSep 2025Qwen3 MaxdeprecatedRetired 2025 flagship, superseded by Qwen3.6+ Max. 256K context…262K$1.20$6.00ReasoningTools / functionsSep 2025Qwen3 Coder PlusdeprecatedAgentic coding model with very long context. Tiered pricing by…1M$1.00$5.00Tools / functionsSep 2025DeepSeek: DeepSeek V3.1 TerminusDeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maint…164K$0.27$1.00ReasoningTools / functionsWeb searchSep 2025Magistral Small (2509)Our efficient reasoning model released September 2025.131K$0.50$1.50VisionReasoningTools / functionsSep 2025Magistral Medium (2509)deprecatedOur frontier-class reasoning model release candidate September…131K$2.00$5.00VisionReasoningTools / functionsSep 2025GPT-5 CodexdeprecatedA version of GPT-5 optimized for agentic coding in Codex.400K$1.25$10.00VisionReasoningTools / functionsWeb searchSep 2025Qwen3 Next 80b A3b ThinkingdeprecatedAlibaba model (not yet curated).131K$0.15$1.20Tools / functionsSep 2025Qwen3 Next 80b A3b InstructAlibaba model (not yet curated).131K$0.09$1.10Tools / functionsSep 2025NVIDIA: Nemotron Nano 9B V2 (free)deprecatedNVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trai…128KFreeFreeReasoningTools / functionsWeb searchSep 2025MoonshotAI: Kimi K2 0905Kimi K2 0905 is the September update of Kimi K2 0711. It is a l…262K$0.60$2.50Tools / functionsWeb searchSep 2025[Groq] Compound Mini (Agentic System)deprecatedLighter Groq agentic AI, same built-in tools but a single tool…131K--Tools / functionsSep 2025[Groq] Compound (Agentic System)deprecatedGroq agentic AI with web search, visit website, code execution,…131K--Tools / functionsSep 2025Qwen3 30b A3b Thinking 2507deprecatedAlibaba model (not yet curated).131K$0.20$2.40Tools / functionsAug 2025GPT AudioFirst generally available audio model. Accepts audio inputs and…128K$2.50$10.00Audio outputAug 2025Nous: Hermes 4 70BdeprecatedHermes 4 70B is a hybrid reasoning model from Nous Research, bu…131K$0.13$0.40ReasoningWeb searchAug 2025Nous: Hermes 4 405BHermes 4 is a large-scale reasoning model built on Meta-Llama-3…131K$1.00$3.00ReasoningWeb searchAug 2025DeepSeek: DeepSeek V3.1DeepSeek-V3.1 is a large hybrid reasoning model (671B parameter…164K$0.25$0.95ReasoningTools / functionsWeb searchAug 2025QWEN3 Embedding 8BdeprecatedModel served on Fireworks AI.41K--Aug 2025Nemotron Nano 9B v2deprecatedSmall hybrid Mamba-Transformer for fast, cheap reasoning and to…128KFreeFreeReasoningTools / functionsAug 2025Mistral: Mistral Medium 3.1Mistral Medium 3.1 is an updated version of Mistral Medium 3, w…131K$0.40$2.00VisionTools / functionsWeb searchAug 2025Mistral Medium (2508)deprecatedUpdate on Mistral Medium 3 with improved capabilities.131K$0.40$2.00VisionTools / functionsAug 2025GLM-4.5 VVision-enabled GLM-4.5 model. 64K context, 16K output, interlea…66K$0.60$1.80VisionReasoningTools / functionsAug 2025Qwen3 4B Instruct 2507Qwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-4…262K--Aug 2025AI21: Jamba Large 1.7deprecatedJamba Large 1.7 is the latest model in the Jamba open family, o…256K$2.00$8.00Tools / functionsWeb searchAug 2025OpenAI: GPT-5 ChatdeprecatedGPT-5 Chat is designed for advanced, natural, multimodal, and c…128K$1.25$10.00VisionAug 2025GPT-5 NanoFastest, most cost-efficient version of GPT-5 for summarization…400K$0.05$0.40VisionReasoningTools / functionsWeb searchImage outputAug 2025GPT-5 MiniA faster, more cost-efficient version of GPT-5 for well-defined…400K$0.25$2.00VisionReasoningTools / functionsWeb searchImage outputAug 2025GPT-5 ChatGPTdeprecatedGPT-5 model used in ChatGPT.128K$1.25$10.00VisionTools / functionsWeb searchImage outputAug 2025GPT-5The best model for coding and agentic tasks across domains.400K$1.25$10.00VisionReasoningTools / functionsWeb searchImage outputAug 2025+2OpenAI: gpt-oss-20bgpt-oss-20b is an open-weight 21B parameter model released by O…131K$0.02$0.09ReasoningTools / functionsWeb searchAug 2025+3OpenAI: gpt-oss-120bgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Exper…131K$0.15$0.60ReasoningTools / functionsWeb searchAug 2025Claude Opus 4.1deprecatedPrevious Opus model. Deprecated June 5, 2026, retiring August 5…200K$15.00$75.00VisionTools / functionsWeb searchAug 2025

CO

Command A TranslateSpecialized machine translation across 23 languages, with tool…9K--Tools / functionsAug 2025

CO

Command A ReasoningReasoning-tuned Command A for multi-step agents and hard proble…289K$2.50$10.00ReasoningTools / functionsAug 2025Qwen: Qwen3 Coder 30B A3B InstructQwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Ex…262K$0.07$0.28Tools / functionsWeb searchJul 2025Glm 4.5 Air Fp8deprecatedZai Org chat model. https://huggingface.co/api/models/zai-org/G…131K$0.20$1.10Jul 2025Codestral (2508)Our cutting-edge language model for coding released August 2025.256K$0.30$0.90Tools / functionsJul 2025Qwen3 30b A3b Instruct 2507Alibaba model (not yet curated).131K$0.10$0.30Tools / functionsJul 2025Qwen3 235B A22b Instruct 2507 Fp8Together AI chat model. https://huggingface.co/api/models/Qwen/…262K--Jul 2025Qwen3 Coder FlashFormer budget coder, superseded by Qwen3.7 Plus. 1M context, no…1M$0.30$1.50Tools / functionsJul 2025GLM-4.5 XExtended GLM-4.5 model. Interleaved thinking.131K$2.20$8.90ReasoningTools / functionsJul 2025GLM-4.5 Flash (Free)Free GLM-4.5 variant with limited concurrency. Prior-gen, super…131KFreeFreeReasoningTools / functionsJul 2025GLM-4.5 AirXExtended lightweight GLM-4.5 variant. Interleaved thinking.131K$1.10$4.50ReasoningTools / functionsJul 2025GLM-4.5 AirLightweight GLM-4.5 variant. Interleaved thinking.131K$0.20$1.10ReasoningTools / functionsJul 2025GLM-4.5Prior-gen GLM-4.5 model with 128K context, 96K output. Interlea…131K$0.60$2.20ReasoningTools / functionsJul 2025Qwen3 235b A22b Thinking 2507Alibaba model (not yet curated).131K$0.45$3.50Tools / functionsJul 2025Qwen3 Coder 480B A35B Instruct Fp8deprecatedQwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-C…262K$2.00$2.00Jul 2025Qwen: Qwen3 Coder 480B A35BQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) co…262K$0.30$1.00Tools / functionsWeb searchJul 2025Qwen3 235B A22B Instruct 2507 FP8 ThroughputdeprecatedQwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-2…262K$0.20$0.60Jul 2025Gemini 2.5 Flash-LiteStable version of Gemini 2.5 Flash-Lite, released in July of 20…1.1M$0.10$0.40VisionReasoningTools / functionsWeb searchJul 2025ByteDance: UI-TARS 7BUI-TARS-1.5 is a multimodal vision-language agent optimized for…128K$0.10$0.20VisionWeb searchJul 2025Qwen: Qwen3 235B A22B Instruct 2507Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tu…262K$0.09$0.55Tools / functionsWeb searchJul 2025Voxtral Small TranscribeA small audio understanding model released in July 202533K$0.10$0.40Tools / functionsJul 2025Voxtral Mini (2507)deprecatedA mini audio understanding model released in July 202533K$0.04$0.04Jul 2025Switchpoint RouterdeprecatedSwitchpoint AI's router instantly analyzes your request and dir…131K$0.85$3.40ReasoningWeb searchJul 2025MoonshotAI: Kimi K2 0711Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) lang…131K$0.57$2.30Tools / functionsWeb searchJul 2025Sarvam MSarvamai chat model. https://huggingface.co/api/models/sarvamai…33K--Jul 2025Meta Llama 3.1 8B Instruct Awq Int4Meta chat model. https://huggingface.co/api/models/togethercomp…131K--Jul 2025Venice: UncensoredVenice Uncensored Dolphin Mistral 24B Venice Edition is a fine-…128K$0.20$0.90Web searchJul 2025Tencent: Hunyuan A13B InstructHunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE)…131K$0.14$0.57ReasoningWeb searchJul 2025Morph: Morph V3 LargeMorph's high-accuracy apply model for complex code edits. ~4,50…262K$0.90$1.90Web searchJul 2025Morph: Morph V3 FastMorph's fastest apply model for code edits. ~10,500 tokens/sec…262K$0.80$1.20Web searchJul 2025

CO

Command A VisionMultimodal Command A for charts, graphs, diagrams, OCR, and doc…128K--VisionJul 2025Baidu: ERNIE 4.5 VL 424B A47BdeprecatedERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE)…123K$0.42$1.25VisionReasoningWeb searchJun 2025Minimax M1 80KMiniMaxAI chat model. https://huggingface.co/api/models/togethe…1M--Jun 2025o4 Mini Deep ResearchdeprecatedFaster, more affordable deep research model for complex, multi-…200K$2.00$8.00VisionReasoningWeb searchJun 2025o3 Deep ResearchdeprecatedOur most powerful deep research model for complex, multi-step r…200K$10.00$40.00VisionReasoningWeb searchJun 2025Minimax M1 40KMiniMaxAI chat model. https://huggingface.co/api/models/togethe…1M--Jun 2025Mistral: Mistral Small 3.2 24BMistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter…256K$0.08$0.20VisionTools / functionsWeb searchJun 2025Mistral Small (2506)deprecatedOur latest enterprise-grade small model with the latest version…131K$0.10$0.30VisionTools / functionsJun 2025Gemini 2.5 ProStable release (June 17th, 2025) of Gemini 2.5 Pro1.1M$1.25$10.00VisionReasoningTools / functionsWeb searchJun 2025Gemini 2.5 FlashStable version of Gemini 2.5 Flash, our mid-size multimodal mod…1.1M$0.30$2.50VisionReasoningTools / functionsWeb searchJun 2025MiniMax M1456B total / 45.9B active MoE with lightning attention. 1M cont…1M$0.40$2.20ReasoningTools / functionsJun 2025Mistral NemotrondeprecatedMistral model post-trained by NVIDIA.262KFreeFreeReasoningTools / functionsJun 2025Magistral Small 2506Mistralai chat model. https://huggingface.co/api/models/mistral…41K--Jun 2025Llama 4 Scout (17Bx16E)Meta chat model. https://huggingface.co/api/models/meta-llama/L…262K--VisionJun 2025o3 ProVersion of o3 with more compute for better responses. Provides…200K$20.00$80.00VisionReasoningTools / functionsWeb searchImage outputJun 2025Gemma 2B ItGoogle chat model. https://huggingface.co/api/models/google/gem…8K--Jun 2025Gemma 2 9B ItGoogle chat model. https://huggingface.co/api/models/google/gem…8K--Jun 2025Qwen3 1.7BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-1…41K--Jun 2025Qwen3 0.6BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-0…41K--Jun 2025Nemotron Nano VL 8BdeprecatedSmall vision-language model, 16K context.16KFreeFreeVisionMay 2025Molmo 7B D 0924Allenai chat model. https://huggingface.co/api/models/allenai/M…4K--VisionMay 2025DeepSeek: R1 0528May 28th update to the original DeepSeek R1 Performance on par…164K$0.50$2.15ReasoningTools / functionsWeb searchMay 2025Mixtral 8X22b Instruct V0.1Mistralai chat model. https://huggingface.co/api/models/mistral…66K--May 2025Anthropic: Claude Sonnet 4deprecatedClaude Sonnet 4 significantly enhances the capabilities of its…200K$3.00$15.00VisionTools / functionsWeb searchMay 2025Anthropic: Claude Opus 4deprecatedClaude Opus 4 is benchmarked as the world’s best coding model,…200K$15.00$75.00VisionTools / functionsWeb searchMay 2025Devstral Small 2505Mistralai chat model. https://huggingface.co/api/models/togethe…131K--May 2025Mistral 7B v0.1Mistralai chat model. https://huggingface.co/api/models/mistral…33K--May 2025Google: Gemma 3n 4BdeprecatedGemma 3n E4B-it is optimized for efficient execution on mobile…33K$0.06$0.12Web searchMay 2025Google: Gemini 2.5 Pro Preview 06-05Gemini 2.5 Pro is Google’s state-of-the-art AI model designed f…1M$1.25$10.00VisionReasoningTools / functionsWeb searchMay 2025Gemini 2.5 Pro Preview TTSGemini 2.5 Pro Preview TTS25K$1.00-VisionAudio outputMay 2025Gemini 2.5 Flash Preview TTSGemini 2.5 Flash Preview TTS25K$0.50-VisionAudio outputMay 2025Deepcoder 14B PreviewTogethercomputer chat model. https://huggingface.co/api/models/…131K--May 2025Mistral: Mistral Medium 3Official mistral-medium-latest Mistral model262K$1.50$7.50VisionReasoningTools / functionsMay 2025Mistral Medium (2505)deprecatedOur frontier-class multimodal model released May 2025.131K$0.40$2.00VisionTools / functionsMay 2025Google: Gemini 2.5 Pro Preview 05-06deprecatedGemini 2.5 Pro is Google’s state-of-the-art AI model designed f…1M$1.25$10.00VisionReasoningTools / functionsWeb searchMay 2025Arcee AI: Virtuoso LargedeprecatedVirtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B…131K$0.75$1.20Tools / functionsWeb searchMay 2025Arcee AI: Coder LargedeprecatedCoder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct…33K$0.50$0.80Web searchMay 2025Meta: Llama Guard 4 12BLlama Guard 4 is a Llama 4 Scout-derived multimodal pretrained…164K$0.18$0.18VisionWeb searchApr 2025Qwen3 8bAlibaba model (not yet curated).131K$0.12$0.46Tools / functionsApr 2025+1Qwen3 32bAlibaba model (not yet curated).131K$0.08$0.28Tools / functionsApr 2025Qwen3 30b A3bAlibaba model (not yet curated).131K$0.12$0.50Tools / functionsApr 2025Qwen3 235b A22bdeprecatedAlibaba model (not yet curated).131K$0.46$1.82Tools / functionsApr 2025Qwen3 14bAlibaba model (not yet curated).131K$0.12$0.24Tools / functionsApr 2025Arize AI Qwen 2 1.5B InstructTogethercomputer chat model. https://huggingface.co/api/models/…33K$0.10$0.10Apr 2025o4 MiniLatest o4-mini model. Optimized for fast, effective reasoning w…200K$1.10$4.40VisionReasoningTools / functionsApr 2025o3A well-rounded and powerful model across domains. Sets a new st…200K$2.00$8.00VisionReasoningTools / functionsApr 2025Llama 3.1 405BMeta chat model. https://huggingface.co/api/models/meta-llama/L…131K--Apr 2025Qwen2.5 7BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…131K--Apr 2025Qwen2.5 72BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…131K--Apr 2025Qwen2.5 3B InstructQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…33K--Apr 2025Qwen2.5 32B InstructQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…33K--Apr 2025Qwen2.5 32BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…131K--Apr 2025Qwen2.5 14BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…131K--Apr 2025Qwen2.5 1.5B InstructQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…33K--Apr 2025Qwen2.5 1.5BQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…131K--Apr 2025Qwen: Qwen2.5 7B InstructQwen2.5 7B is the latest series of Qwen large language models.…33K$0.10$0.20Tools / functionsWeb searchApr 2025Llama 3.2 1BMeta chat model. https://huggingface.co/api/models/meta-llama/L…131K--Apr 2025Llama 3.1 70BMeta chat model. https://huggingface.co/api/models/meta-llama/L…131K--Apr 2025GPT-4.1 NanoFastest, most cost-effective GPT 4.1 model. Delivers exceptiona…1M$0.10$0.40VisionTools / functionsApr 2025GPT-4.1 MiniBalanced for intelligence, speed, and cost. Matches or exceeds…1M$0.40$1.60VisionTools / functionsApr 2025GPT-4.1Flagship GPT model for complex tasks. Major improvements on cod…1M$2.00$8.00VisionTools / functionsApr 2025GLM-4 32B (0414) 128KGLM-4 32B model with 128K context, 16K output.131K$0.10$0.10Tools / functionsApr 2025Qwen2 72B InstructdeprecatedTogethercomputer chat model. https://huggingface.co/api/models/…33K$0.90$0.90Apr 2025Cogito V1 Preview Qwen 32Bdeepcogito chat model.131K--Apr 2025Cogito V1 Preview Qwen 14Bdeepcogito chat model.131K--Apr 2025Cogito V1 Preview Llama 8Bdeepcogito chat model.131K--Apr 2025Cogito V1 Preview Llama 70B Turbodeepcogito chat model.131K--Apr 2025Cogito V1 Preview Llama 70Bdeepcogito chat model.131K--Apr 2025Meta: Llama 4 ScoutLlama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE)…328K$0.10$0.30VisionTools / functionsWeb searchApr 2025Meta: Llama 4 MaverickLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimo…524K$0.19$0.65VisionTools / functionsWeb searchApr 2025Llama 4 Scout Instruct (17Bx16E)deprecatedMeta chat model. https://huggingface.co/meta-llama/Llama-4-Scou…1M$0.18$0.59Apr 2025Gemma 3 1b itGoogle chat model.33K--Apr 2025DeepSeek R1 Distill Qwen 7BDeepseek chat model. https://huggingface.co/deepseek-ai/DeepSee…131K--Apr 2025meta-llama/Llama-2-7b-chat-hfMeta chat model. https://huggingface.co/meta-llama/Llama-2-7b-c…4K--Apr 2025DeepSeek: DeepSeek V3 0324DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the…164K$0.29$1.14Tools / functionsWeb searchMar 2025o1 ProA version of o1 with more compute for better responses. Provide…200K$150.00$600.00VisionReasoningTools / functionsMar 2025Llama 3.3 Nemotron Super 49B v1Superseded by v1.5.131KFreeFreeReasoningTools / functionsMar 2025Mistral: Mistral Small 3.1 24BMistral Small 3.1 24B Instruct is an upgraded variant of Mistra…128K$0.35$0.56VisionTools / functionsWeb searchMar 2025nim/nv-mistralai/mistral-nemo-12b-instructNVIDIA chat model.16K--Mar 2025nim/mistralai/mixtral-8x7b-instruct-v01mistralai chat model.16K--Mar 2025Google: Gemma 3 4BGemma 3 introduces multimodality, supporting vision-language in…131K$0.05$0.10VisionWeb searchMar 2025Google: Gemma 3 12BGemma 3 introduces multimodality, supporting vision-language in…131K$0.05$0.15VisionTools / functionsWeb searchMar 2025

CO

Cohere: Command ACommand A is an open-weights 111B parameter model with a 256k c…256K$2.50$10.00Web searchMar 2025Reka Flash 3Reka Flash 3 is a general-purpose, instruction-tuned large lang…66K$0.10$0.20ReasoningWeb searchMar 2025nim/nvidia/llama-3.1-nemotron-70b-instructNVIDIA chat model.16K--Mar 2025Google: Gemma 3 27BGemma 3 introduces multimodality, supporting vision-language in…131K$0.08$0.35VisionTools / functionsWeb searchMar 2025GPT-4o Search PreviewdeprecatedGPT-4o model optimized for web search capabilities. Alias still…128K$2.50$10.00Web searchMar 2025GPT-4o Mini Search PreviewdeprecatedGPT-4o Mini model optimized for web search capabilities. Alias…128K$0.15$0.60Web searchMar 2025TheDrummer: Skyfall 36B V2Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501,…33K$0.55$0.80Web searchMar 2025nim/mistralai/mixtral-8x22b-instruct-v01Mistral chat model.16K--Mar 2025Meta Llama 3.1 8B Instruct TurbodeprecatedMeta chat model. https://huggingface.co/meta-llama/Meta-Llama-3…131K$0.18$0.18Mar 2025Qwen QwQ-32BdeprecatedQwen chat model. https://huggingface.co/Qwen/QwQ-32B131K$1.20$1.20Mar 2025

CO

Aya Vision 32BOpen-weights multilingual vision research model (23 languages)…16K$0.50$1.50VisionMar 2025Sonar Reasoning ProPremier reasoning model with enhanced multi-step Chain of Thoug…128K$2.00$8.00VisionReasoningWeb searchFeb 2025Mistral: SabaMistral Saba is a 24B-parameter language model specifically des…33K$0.20$0.60Tools / functionsWeb searchFeb 2025Sonar Deep ResearchExpert-level research model for exhaustive searches and compreh…128K$2.00$8.00VisionReasoningWeb searchFeb 2025Gemini 2.0 Flash 001deprecatedStable version of Gemini 2.0 Flash, our fast and versatile mult…1.1M$0.10$0.40VisionTools / functionsFeb 2025AionLabs: Aion-RP 1.0 (8B)Aion-RP-Llama-3.1-8B ranks the highest in the character evaluat…33K$0.80$1.60Web searchFeb 2025AionLabs: Aion-1.0-MinideprecatedAion-1.0-Mini 32B parameter model is a distilled version of the…131K$0.70$1.40ReasoningWeb searchFeb 2025AionLabs: Aion-1.0deprecatedAion-1.0 is a multi-model system designed for high performance…131K$4.00$8.00ReasoningWeb searchFeb 2025Qwen: Qwen2.5 VL 72B InstructQwen2.5-VL is proficient in recognizing common objects such as…128K$0.80$1.00VisionWeb searchFeb 2025

CO

Command R7B ArabicCommand R7B tuned for Modern Standard Arabic and English enterp…128K$0.04$0.15Tools / functionsFeb 2025o3 MiniLatest o3-mini model snapshot. High intelligence at the same co…200K$1.10$4.40ReasoningTools / functionsJan 2025Mistral: Mistral Small 3Mistral Small 3 is a 24B-parameter language model optimized for…33K$0.05$0.08Web searchJan 2025DeepSeek R1 Distill Qwen 14BdeprecatedDeepSeek chat model. https://huggingface.co/api/models/deepseek…131K$1.60$1.60Jan 2025DeepSeek R1 Distill Qwen 1.5BdeprecatedDeepSeek chat model. https://huggingface.co/deepseek-ai/DeepSee…131K$0.18$0.18Jan 2025DeepSeek: R1 Distill Llama 70BdeprecatedDeepSeek R1 Distill Llama 70B is a distilled large language mod…8K$0.80$0.80ReasoningWeb searchJan 2025Sonar ProAdvanced search model for complex queries and deep content unde…200K$3.00$15.00VisionWeb searchJan 2025SonarLightweight, cost-effective search model for quick, grounded an…128K$1.00$1.00VisionWeb searchJan 2025DeepSeek: R1deprecatedDeepSeek R1 is here: Performance on par with OpenAI o1, but ope…64K$0.70$2.50ReasoningTools / functionsWeb searchJan 2025NemoGuard 8B Topic ControlNVIDIA topic-control guardrail (not a chat model).131KFreeFreeJan 2025NemoGuard 8B Content SafetyNVIDIA content-safety classifier (not a chat model).131KFreeFreeJan 2025V1 8K Vision (Preview)deprecatedLegacy vision model with 8K context. Sunset on 2026-08-31 - use…8K$0.20$2.00VisionJan 2025V1 32K Vision (Preview)deprecatedLegacy vision model with 32K context. Sunset on 2026-08-31 - us…33K$1.00$3.00VisionJan 2025V1 128K Vision (Preview)deprecatedLegacy vision model with 128K context. Sunset on 2026-08-31 - u…131K$2.00$5.00VisionJan 2025MiniMax Text 01Legacy flagship. 1M context, 40K max output.1M$0.20$1.10Tools / functionsJan 2025MiniMax 01Legacy flagship. 1M context.1M$0.20$1.10Tools / functionsJan 2025Microsoft: Phi 4Microsoft Research Phi-4 is designed to perform well in complex…16K$0.07$0.14Web searchJan 2025Qwen2-VL (72B) InstructdeprecatedQwen chat model. https://huggingface.co/Qwen/Qwen2-VL-72B-Instr…33K$1.20$1.20VisionJan 2025Sao10K: Llama 3.1 70B Hanami x1deprecatedThis is Sao10K's experiment over Euryale v2.2.16K$3.00$3.00Jan 2025DeepSeek: DeepSeek V3DeepSeek-V3 is the latest model from the DeepSeek team, buildin…164K$0.26$1.03Tools / functionsWeb searchDec 2024Sao10K: Llama 3.3 Euryale 70BdeprecatedEuryale L3.3 70B is a model focused on creative roleplay from S…131K$0.65$0.75Dec 2024o1Previous full o-series reasoning model.200K$15.00$60.00VisionReasoningTools / functionsDec 2024

CO

Cohere: Command R7B (12-2024)Command R7B (12-2024) is a small, fast update of the Command R+…128K$0.04$0.15Web searchDec 2024Qwen 2.5 14B InstructdeprecatedQwen chat model. https://huggingface.co/api/models/Qwen/Qwen2.5…33K$0.80$0.80Dec 2024Qwen2.5 72B InstructdeprecatedQwen chat model. https://huggingface.co/Qwen/Qwen2.5-72B-Instru…33K$1.20$1.20Dec 2024Meta: Llama 3.3 70B InstructThe Meta Llama 3.3 multilingual large language model (LLM) is a…131K$0.10$0.32Tools / functionsWeb searchDec 2024Meta Llama 3.3 70B Instruct TurboMeta chat model. https://huggingface.co/meta-llama/Llama-3.3-70…131K$1.04$1.04Dec 2024Meta Llama 3.1 405B InstructdeprecatedMeta chat model. https://huggingface.co/meta-llama/Llama-3.1-40…4K$3.50$3.50Dec 2024[Meta] Llama 3.3 · 70B VersatiledeprecatedMeta Llama 3.3 (70B params) with GQA. Strong reasoning, coding,…131K$0.59$0.79Tools / functionsDec 2024Amazon: Nova Pro 1.0Amazon Nova Pro 1.0 is a capable multimodal model from Amazon f…300K$0.80$3.20VisionTools / functionsWeb searchDec 2024Amazon: Nova Micro 1.0Amazon Nova Micro 1.0 is a text-only model that delivers the lo…128K$0.04$0.14Tools / functionsWeb searchDec 2024Amazon: Nova Lite 1.0Amazon Nova Lite 1.0 is a very low-cost multimodal model from A…300K$0.06$0.24VisionTools / functionsWeb searchDec 2024Mistral Large 2407This is Mistral AI's flagship model, Mistral Large 2 (version m…131K$2.00$6.00Tools / functionsWeb searchNov 2024Qwen 2.5 Coder 32B InstructdeprecatedQwen chat model. https://huggingface.co/Qwen/Qwen2.5-Coder-32B-…16K$0.80$0.80Nov 2024Qwen2.5 Coder 32B InstructQwen2.5-Coder is the latest series of Code-Specific Qwen large…33K$0.66$1.00Web searchNov 2024Llama 3.1 Nemotron 70B Instruct HFdeprecatednvidia chat model. https://huggingface.co/nvidia/Llama-3.1-Nemo…33K$0.88$0.88Nov 2024TheDrummer: UnslopNemo 12BUnslopNemo v4.1 is the latest addition from the creator of Roci…1M$0.40$0.40Web searchNov 2024Magnum v4 72BThis is a series of models designed to replicate the prose qual…33K$2.50$5.00Web searchOct 2024Mistral: Ministral 8BdeprecatedMinistral 8B is an 8B parameter model featuring a unique interl…128K$0.11$0.11Web searchOct 2024Qwen2.5 7B Instruct TurbodeprecatedQwen chat model. https://huggingface.co/Qwen/Qwen2.5-7B-Instruct33K$0.30$0.30Oct 2024Qwen2.5 72B Instruct TurbodeprecatedQwen chat model. https://huggingface.co/Qwen/Qwen2.5-72B-Instru…131K$1.20$1.20Oct 2024Inflection: Inflection 3 ProductivitydeprecatedInflection 3 Productivity is optimized for following instructio…8K$2.50$10.00Web searchOct 2024Inflection: Inflection 3 PideprecatedInflection 3 Pi powers Inflection's Pi chatbot, including backs…8K$2.50$10.00Web searchOct 2024

CO

Aya Expanse 32BOpen-weights multilingual research model covering 23 languages.…128K$0.50$1.50Oct 2024TheDrummer: Rocinante 12BdeprecatedRocinante 12B is designed for engaging storytelling and rich pr…66K$0.25$0.50Web searchSep 2024Meta: Llama 3.2 3B InstructLlama 3.2 3B is a 3-billion-parameter multilingual large langua…131K$0.05$0.33Web searchSep 2024Meta: Llama 3.2 1B InstructLlama 3.2 1B is a 1-billion-parameter language model focused on…60K$0.03$0.20Web searchSep 2024Meta: Llama 3.2 11B Vision InstructLlama 3.2 11B Vision is a multimodal model with 11 billion para…131K$0.35$0.35VisionWeb searchSep 2024Llama 3.2 90B VisionLlama large vision model. NVIDIA serves a reduced 32K context (…33KFreeFreeVisionSep 2024Qwen2.5 72B InstructQwen2.5 72B is the latest series of Qwen large language models.…33K$0.36$0.40Tools / functionsWeb searchSep 2024Nemotron Mini 4BdeprecatedTiny legacy Nemotron, 4K context.4KFreeFreeTools / functionsSep 2024

CO

Cohere: Command R+ (08-2024)command-r-plus-08-2024 is an update of the Command R+ with roug…128K$2.50$10.00Tools / functionsWeb searchAug 2024

CO

Cohere: Command R (08-2024)command-r-08-2024 is an update of the Command R with improved p…128K$0.15$0.60Tools / functionsWeb searchAug 2024Sao10K: Llama 3.1 Euryale 70B v2.2Euryale L3.1 70B v2.2 is a model focused on creative roleplay f…131K$0.85$0.85Web searchAug 2024Nous: Hermes 3 70B InstructHermes 3 is a generalist language model with many improvements…131K$0.70$0.70Web searchAug 2024Nous: Hermes 3 405B InstructHermes 3 is a generalist language model with many improvements…131K$1.00$1.00Web searchAug 2024Sao10K: Llama 3 8B LunarisLunaris 8B is a versatile generalist and roleplaying model base…8K$0.04$0.05Web searchAug 2024Meta: Llama 3.1 8B InstructMeta's latest class of model (Llama 3.1) launched with a variet…131K$0.05$0.08Tools / functionsWeb searchJul 2024Meta: Llama 3.1 70B InstructMeta's latest class of model (Llama 3.1) launched with a variet…131K$0.40$0.40Tools / functionsWeb searchJul 2024[Meta] Llama 3.1 · 8B InstantdeprecatedMeta Llama 3.1 (8B params). Fast, cost-effective for high-volum…131K$0.05$0.08Tools / functionsJul 2024Meta Llama 3.1 70B Instruct TurbodeprecatedMeta chat model. https://huggingface.co/meta-llama/Meta-Llama-3…131K$0.88$0.88Jul 2024Mistral: Mistral NemoA 12B parameter model with a 128k token context length built by…131K$0.03$0.03Tools / functionsWeb searchJul 2024open-mistral-nemo-2407deprecatedOur best multilingual open source model released July 2024.131K$0.15$0.15Tools / functionsJul 2024open-mistral-nemodeprecatedOur best multilingual open source model released July 2024.131K$0.15$0.15Tools / functionsJul 2024GPT-4o miniAffordable model for fast, lightweight tasks. GPT-4o Mini is ch…128K$0.15$0.60VisionTools / functionsJul 2024Google: Gemma 2 27BGemma 2 27B by Google is an open model built from the same rese…8K$0.65$0.65Web searchJul 2024Qwen 2 Instruct (1.5B)deprecatedQwen chat model. https://huggingface.co/Qwen/Qwen2-72B-Instruct33K$0.02$0.02Jun 2024Mistral (7B) Instruct v0.3deprecatedmistralai chat model. https://huggingface.co/api/models/mistral…33K$0.20$0.20May 2024GPT-4oSnapshot that supports Structured Outputs. gpt-4o currently128K$2.50$10.00VisionTools / functionsMay 2024Meta: Llama 3 8B InstructdeprecatedMeta's latest class of model (Llama 3) launched with a variety…8K$0.14$0.14Web searchApr 2024Meta Llama 3 8B Instruct ReferencedeprecatedMeta chat model. https://huggingface.co/meta-llama/Meta-Llama-3…8K$0.20$0.20Apr 2024Meta Llama 3 8B InstructdeprecatedMeta chat model. https://huggingface.co/meta-llama/Meta-Llama-3…8K$0.20$0.20Apr 2024Mistral: Mixtral 8x22B InstructMistral's official instruct fine-tuned version of Mixtral 8x22B…66K$2.00$6.00Tools / functionsWeb searchApr 2024WizardLM-2 8x22BdeprecatedWizardLM-2 8x22B is Microsoft AI's most advanced Wizard model.…66K$0.62$0.62Web searchApr 2024GPT-4 TurboGPT-4 Turbo with Vision model. Vision requests can now use JSON…128K$10.00$30.00VisionTools / functionsApr 2024Anthropic: Claude 3 HaikuClaude 3 Haiku is Anthropic's fastest and most compact model fo…200K$0.25$1.25VisionTools / functionsMar 2024Mistral LargeThis is Mistral AI's flagship model, Mistral Large 2 (version `…128K$2.00$6.00Tools / functionsWeb searchFeb 2024Deepseek Coder 33B InstructdeprecatedDeepseek chat model. https://huggingface.co/api/models/deepseek…16K$0.80$0.80Feb 2024V1 8KdeprecatedLegacy V1 model with 8K context. Sunset on 2026-08-31 - use Kim…8K$0.20$2.00Tools / functionsFeb 2024V1 32KdeprecatedLegacy V1 model with 32K context. Sunset on 2026-08-31 - use Ki…33K$1.00$3.00Tools / functionsFeb 2024V1 128KdeprecatedLegacy V1 model with 128K context. Sunset on 2026-08-31 - use K…131K$2.00$5.00Tools / functionsFeb 2024OpenAI: GPT-4 Turbo PreviewdeprecatedThe preview GPT-4 model with improved instruction following, JS…128K$10.00$30.00Tools / functionsWeb searchJan 2024OpenAI: GPT-3.5 Turbo (older v0613)GPT-3.5 Turbo is OpenAI's fastest model. It can understand and…4K$1.00$2.00Tools / functionsWeb searchJan 20243.5-TurbodeprecatedThe latest GPT-3.5 Turbo model with higher accuracy at respondi…16K$0.50$1.50Tools / functionsJan 2024Nous Hermes 2 Mixtral 8X7B DpodeprecatedNousresearch chat model. https://huggingface.co/api/models/Nous…33K$0.60$0.60Jan 2024Mixtral-8x7B Instruct v0.1deprecatedmistralai chat model. https://huggingface.co/mistralai/Mixtral-…33K$0.60$0.60Dec 2023Auto RouterThe Auto Router automatically selects the best model for your p…2M--VisionReasoningTools / functionsWeb searchImage outputNov 20233.5-TurbodeprecatedGPT-3.5 Turbo model with improved instruction following, JSON m…16K$1.00$2.00Tools / functionsNov 2023OpenAI: GPT-3.5 Turbo InstructdeprecatedThis model is a variant of GPT-3.5 Turbo tuned for instructiona…4K$1.50$2.00Sep 2023Mistral (7B) Instruct v0.1deprecatedmistralai chat model. https://huggingface.co/api/models/mistral…33K$0.20$0.20Sep 2023OpenAI: GPT-3.5 Turbo 16kThis model offers four times the context length of gpt-3.5-turb…16K$3.00$4.00Tools / functionsWeb searchAug 2023Mancer: Weaver (alpha)An attempt to recreate Claude-style verbosity, but don't expect…8K$0.40$0.75Web searchAug 2023ReMM SLERP 13BA recreation trial of the original MythoMax-L2-B13 but with upd…6K$0.35$0.65Web searchJul 2023MythoMax 13BOne of the highest performing and most popular fine-tunes of Ll…8K$0.08$0.11Web searchJul 2023GPT-4Snapshot of gpt-4 from June 13th 2023 with improved function ca…8K$30.00$60.00Tools / functionsJun 2023GPT-4deprecatedSnapshot of gpt-4 from June 13th 2023 with improved function ca…8K$30.00$60.00Tools / functionsJun 20233.5-TurboThe latest GPT-3.5 Turbo model with higher accuracy at respondi…16K$0.50$1.50Tools / functionsMay 2023? [gpt live transcribe]deprecatedUnknown, please let us know the ID. Assuming a context window o…128K--VisionTools / functions-? [gpt transcribe]deprecatedUnknown, please let us know the ID. Assuming a context window o…128K--VisionTools / functions-? [ra gpt 5.6 sol]deprecatedUnknown, please let us know the ID. Assuming a context window o…128K--VisionTools / functions-AI21 Labs Jamba 1.5 LargedeprecatedAI21 Labs model via Unsupported API (Bedrock Foundation Model)----AI21 Labs Jamba 1.5 MinideprecatedAI21 Labs model via Unsupported API (Bedrock Foundation Model)----Amazon Nova 2 LiteAmazon model via Converse API (Bedrock Inference Profile)---Tools / functions-Amazon Nova 2.5 SonicAmazon model via Converse API (Bedrock Foundation Model)---Tools / functionsAudio output-Amazon Nova LiteAmazon model via Converse API (Bedrock Foundation Model)---VisionTools / functions-Amazon Nova MicroAmazon model via Converse API (Bedrock Foundation Model)---Tools / functions-Amazon Nova PremierAmazon model via Converse API (Bedrock Inference Profile)---Tools / functions-Amazon Nova ProAmazon model via Converse API (Bedrock Foundation Model)10K--VisionTools / functions-Anthropic Claude 3 SonnetAnthropic model (Bedrock Inference Profile)200K--VisionTools / functions-Anthropic HoneydeprecatedAnthropic model via OpenAI-Compatible API on AWS Bedrock Mantle131K---Cohere Command RdeprecatedCohere model via Unsupported API (Bedrock Foundation Model)----Cohere Command R+deprecatedCohere model via Unsupported API (Bedrock Foundation Model)----Cohere Embed v4deprecatedCohere model via Converse API (Bedrock Inference Profile)---Tools / functions-DeepSeek-R1Deepseek model via Converse API (Bedrock Inference Profile)---Tools / functions-FLUX.2 Klein 4BdeprecatedModel served via Modular.---Tools / functions-Gemma 4 12B ItGoogle chat model. https://huggingface.co/google/gemma-4-12B-it262K--Vision-Glm 5 3 ShortdeprecatedOfficial Z.ai GLM 5.3 model, 256k context262K--ReasoningTools / functions-GLM 5.2 FP8 LoraZai Org chat model. https://huggingface.co/api/models/zai-org/G…1M---GLM 5.3 FP8 LoraZai Org chat model. https://huggingface.co/api/models/zai-org/G…1M---glm-5-3-shortdeprecatedOfficial Z.ai GLM 5.3 model, 256k context262K--ReasoningTools / functions-GLM-5.2 Fast (Alibaba)Zhipu GLM-5.2 fast-serving tier via Alibaba Model Studio (previ…1M$2.80$8.80ReasoningTools / functions-Google Gemma 4 26b A4bGoogle model via OpenAI-Compatible API on AWS Bedrock Mantle131K--Tools / functions-Google Gemma 4 31bGoogle model via OpenAI-Compatible API on AWS Bedrock Mantle131K$0.99$1.49Tools / functions-Google Gemma 4 E2bGoogle model via OpenAI-Compatible API on AWS Bedrock Mantle131K--Tools / functions-GPT-6 AstradeprecatedMost capable OpenAI model, built for the hardest end-to-end wor…1.1M$10.00$50.00VisionReasoningTools / functionsWeb searchImage output-Kimi K2.5 Fp4deprecatedTogethercomputer chat model. https://huggingface.co/api/models/…262K$0.50$2.80-LFM2-24B-A2BdeprecatedTogethercomputer chat model.33K$0.03$0.12-LFM2.5-8B-A1BdeprecatedLiquidAI chat model. https://huggingface.co/api/models/LiquidAI…128K$0.03$0.12-Meta Llama 3 70B InstructMeta model via Converse API (Bedrock Foundation Model)---Tools / functions-Meta Llama 3 70B Instruct TurbodeprecatedMeta chat model. https://huggingface.co/meta-llama/Meta-Llama-3…8K$0.88$0.88-Meta Llama 3 8B InstructMeta model via Converse API (Bedrock Foundation Model)---Tools / functions-Meta Llama 3 8B Instruct LitedeprecatedMeta chat model. https://huggingface.co/meta-llama/Meta-Llama-3…8K$0.14$0.14-Meta Llama 3.1 70B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 3.1 8B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 3.2 11B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 3.2 1B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 3.2 3B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 3.2 90B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 3.3 70B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 4 Maverick 17B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-Meta Llama 4 Scout 17B InstructMeta model via Converse API (Bedrock Inference Profile)---Tools / functions-MiniMax M3MiniMax 428B MoE (23B active) with Sparse Attention for efficie…512K$0.30$1.20ReasoningTools / functions-Mistral AI Devstral 2 123BMistral AI model via OpenAI-Compatible API (Bedrock Foundation…262K--Tools / functions-Mistral AI Ministral 14B 3.0Mistral AI model via OpenAI-Compatible API (Bedrock Foundation…262K--VisionTools / functions-Mistral AI Ministral 3 8BMistral AI model via OpenAI-Compatible API (Bedrock Foundation…262K--VisionTools / functions-Mistral AI Ministral 3BMistral AI model via OpenAI-Compatible API (Bedrock Foundation…262K--VisionTools / functions-Mistral AI Mistral 7B InstructMistral AI model via Converse API (Bedrock Foundation Model)---Tools / functions-Mistral AI Mistral Large (24.02)Mistral AI model via Converse API (Bedrock Foundation Model)---Tools / functions-Mistral AI Mistral Large 3Mistral AI model via OpenAI-Compatible API (Bedrock Foundation…262K--VisionTools / functions-Mistral AI Mistral Small (24.02)Mistral AI model via Converse API (Bedrock Foundation Model)---Tools / functions-Mistral AI Mixtral 8x7B InstructMistral AI model via Converse API (Bedrock Foundation Model)---Tools / functions-Mistral AI Voxtral Mini 3B 2507Mistral AI model via OpenAI-Compatible API (Bedrock Foundation…33K--Tools / functions-Mistral Large 4 0 8deprecatedMistral Large 4.0.8 (Patchstral) MOPD checkpoint (step 350), wi…1M--VisionReasoningTools / functions-Mistral Pixtral Large 25.02Mistral model via Converse API (Bedrock Inference Profile)---Tools / functions-mistral-large-4-0-8deprecatedMistral Large 4.0.8 (Patchstral) MOPD checkpoint (step 350), wi…1M--VisionReasoningTools / functions-Muse Spark Open 816B A42B Promo (Free until 10/18)deprecatedMeta chat model.1M---

CO

north small translate 1.0New Cohere Model128K---NVIDIA Nemotron 3 Super 120B A12BNVIDIA model via OpenAI-Compatible API (Bedrock Foundation Mode…262K--Tools / functions-NVIDIA Nemotron Nano 12B v2 VL BF16NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Mode…131K--VisionTools / functions-NVIDIA Nemotron Nano 3 30BNVIDIA model via OpenAI-Compatible API (Bedrock Foundation Mode…262K--Tools / functions-NVIDIA Nemotron Nano 9B v2NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Mode…131K--Tools / functions-Open Mistral NemodeprecatedOur best multilingual open source model released July 2024.131K--Tools / functions-Openai Gpt 6 Astra MinordeprecatedOpenai model via OpenAI-Compatible API on AWS Bedrock Mantle131K--Tools / functions-OpenAI GPT OSS Safeguard 120BOpenAI model via OpenAI-Compatible API (Bedrock Foundation Mode…131K--ReasoningTools / functions-OpenAI gpt-oss-120bOpenAI model via Converse API (Bedrock Foundation Model)128K--Tools / functions-OpenAI gpt-oss-20bOpenAI model via Converse API (Bedrock Foundation Model)128K--Tools / functions-

CO

parse v5.0deprecatedNew Cohere Model128K---Qvq MaxdeprecatedAlibaba model (not yet curated).131K--Tools / functions-Qwen Coder PlusdeprecatedAlibaba model (not yet curated).131K--Tools / functions-Qwen FlashFast and very low cost with hybrid thinking. 1M context.1M$0.05$0.40ReasoningTools / functions-Qwen MaxBest quality of the stable commercial line. 32K context.33K$1.60$6.40Tools / functions-Qwen PlusBalanced quality, speed, and cost with hybrid thinking. 1M cont…1M$0.40$1.20ReasoningTools / functions-Qwen PlusBalanced quality, speed, and cost with hybrid thinking. 1M cont…1M$0.40$1.20ReasoningTools / functions-Qwen TurbodeprecatedFastest and cheapest for simple tasks. 1M context.1M$0.05$0.20Tools / functions-Qwen Vl MaxdeprecatedAlibaba model (not yet curated).131K--Tools / functions-Qwen Vl PlusdeprecatedAlibaba model (not yet curated).131K--Tools / functions-Qwen3 235b A22b Instruct 2507deprecatedAlibaba model (not yet curated).131K--Tools / functions-Qwen3 Coder 480b A35b InstructAlibaba model (not yet curated).131K--Tools / functions-Qwen3 Coder Next Fp8deprecatedQwen chat model. https://huggingface.co/api/models/Qwen/Qwen3-C…262K$0.50$1.20-Qwen3 MaxdeprecatedRetired 2025 flagship, superseded by Qwen3.6+ Max. 256K context…262K$1.20$6.00ReasoningTools / functions-Qwen3 Next 80B A3BQwen model via Converse API (Bedrock Foundation Model)262K--Tools / functions-Qwen3 VL 235B A22BQwen model via Converse API (Bedrock Foundation Model)262K--VisionTools / functions-Qwen3 VL PlusCurrent vision-language model with strong visual reasoning and…262K$0.20$1.60VisionReasoningTools / functions-Qwen3.5 35B A3B LoraQwen chat model.262K--Vision-Qwen3.7 MaxFlagship agent model with native extended thinking and 1M conte…1M$2.50$7.50ReasoningTools / functions-Qwq PlusdeprecatedAlibaba model (not yet curated).131K--Tools / functions-Tev1 4B ExperimentaldeprecatedTogether AI chat model.33K$0.04--TwelveLabs Marengo Embed 3.0deprecatedTwelvelabs model via Converse API (Bedrock Inference Profile)---Tools / functions-TwelveLabs Marengo Embed v2.7deprecatedTwelvelabs model via Converse API (Bedrock Inference Profile)---Tools / functions-Twelvelabs Pegasus v1.2Twelvelabs model via Converse API (Bedrock Inference Profile)---Tools / functions-TwelveLabs Pegasus v1.5Twelvelabs model via Converse API (Bedrock Inference Profile)---Tools / functions-Writer Palmyra Vision 7BWriter model via OpenAI-Compatible API (Bedrock Foundation Mode…4K--Vision-Writer Palmyra X4Writer model via Converse API (Bedrock Inference Profile)---Tools / functions-Zai Glm 5 3 FlashGLM 5.3 Flash with a 1M context limit1M--VisionReasoningTools / functions-zai-glm-5-3-shortdeprecatedOfficial Z.ai GLM 5.3 model, 256k context262K--ReasoningTools / functions-zai-glm-5-latest-shortdeprecatedOfficial Z.ai GLM 5.3 model, 256k context262K--ReasoningTools / functions-
Showing 805 of 805 models · prices in USD per 1M tokens · refreshed hourly

Common questions

FAQ

How many AI models does Big-AGI support?

Big-AGI connects to 800+ models across 30+ providers, including Anthropic, OpenAI, Google Gemini, SpaceXAI (formerly xAI), DeepSeek, Mistral, Perplexity, Groq, NVIDIA, and OpenRouter. New models are usually added the day they ship. The index above lists the models currently tracked, with capabilities, context windows, and pricing.

How much do the models cost?

You bring your own provider API keys and pay standard provider rates. Big-AGI adds no markup on model usage and never limits your access. Prices above are in USD per 1M tokens, split into input and output. They cover text tokens only and do not include image, audio, or other multimodal input and output, or provider fees for requests, tools, caching, and other services. Prices can change and may be out of date, so always check the provider for current rates. The optional Pro plan ($10.99/mo) covers cross-device sync and does not restrict model usage.

What is the context window, and which model has the largest?

The context window is how much text a model can hold at once, measured in tokens and shown per model. Sort the Context column to rank every model from largest to smallest. Values change as providers ship new versions, so the table always reflects the current numbers.

Can I compare models side by side?

Yes. Filter and sort the table by vendor, context, price, or capability to compare specs directly. Inside Big-AGI, Beam runs 2 to 24 models in parallel on the same prompt, then compares or merges their answers, so you judge real output, not just specs.

Are my API keys and chats private?

Keys and chats are stored in your browser, local first. With Direct Connection on, requests go straight from your browser to the provider and never pass through the Big-AGI servers (requires a browser-side key and provider CORS support). The Big-AGI core is open source under the MIT license.

Can I run local or open-source models?

Yes. Big-AGI connects to local runtimes like LocalAI, Ollama, and LM Studio, and you can mix local and cloud models in the same chat. Any OpenAI-compatible endpoint is auto-detected by hostname.

Run any of these in Big-AGI.

Connect your own keys, run models side by side, then compare and merge the answers. Keys stay in your browser.

Launch Big-AGI

Alibaba

Anthropic

AWS Bedrock

Azure

Cerebras

DeepSeek

Fireworks AI

Google Gemini

Groq

Meta

MiniMax

Mistral

Modular

Moonshot

NVIDIA

OpenAI

OpenRouter

Perplexity

Sakana AI

SpaceXAI

Together AI

Z.ai

BIG-AGI

Product

FeaturesModelsControlsWhat's newBEAM Technology

Resources

DocumentationDiscordGitHub

Company

Email UsPrivacyTerms

© 2026 Token Fabrics·Built with passion in San Diego