OpenAI
GPT 4.1
openai/gpt-4.1Flagship model with 200K context, best for complex reasoning and coding
Context200KMax Output33KInput$2.10/MOutput$8.40/M
ChatVisionCode
K
109 models
OpenAI
GPT 4.1 Mini
openai/gpt-4.1-miniFast and affordable, great balance of speed and intelligence
Context200KMax Output33KInput$0.42/MOutput$1.68/M
ChatVisionCode
OpenAI
GPT 4.1 Nano
openai/gpt-4.1-nanoFastest and cheapest, ideal for simple tasks and classification
Context200KMax Output33KInput$0.10/MOutput$0.42/M
ChatCode
OpenAI
GPT 4o
openai/gpt-4oPrevious flagship with vision, strong all-around performance
Context128KMax Output16KInput$2.63/MOutput$10.50/M
ChatVisionCode
OpenAI
GPT 4o Mini
openai/gpt-4o-miniCompact model optimized for speed and cost efficiency
Context128KMax Output16KInput$0.16/MOutput$0.63/M
ChatVisionCode
OpenAI
GPT 4o Audio Preview
openai/gpt-4o-audio-previewMultimodal model supporting audio input and output
Context128KMax Output16KInput$2.63/MOutput$10.50/M
ChatVisionAudio
OpenAI
O3
openai/o3Latest reasoning model with improved speed and accuracy
Context200KMax Output100KInput$2.10/MOutput$8.40/M
ChatReasoningCode
OpenAI
O3 Mini
openai/o3-miniEfficient reasoning model, best value for thinking tasks
Context200KMax Output66KInput$1.16/MOutput$4.62/M
ChatReasoningCode
OpenAI
O4 Mini
openai/o4-miniNewest compact reasoning model with tool use support
Context200KMax Output100KInput$1.16/MOutput$4.62/M
ChatReasoningCode
OpenAIFREE
Dall E 3
openai/dall-e-3State-of-the-art image generation from text prompts
FREE
Image Gen
OpenAI
TTS 1
openai/tts-1Standard text-to-speech, fast and natural sounding
Input$15.75/MOutput$0/M
TTS
OpenAI
TTS 1 Hd
openai/tts-1-hdHigh-definition text-to-speech with premium voice quality
Input$31.50/MOutput$0/M
TTS
OpenAIFREE
Whisper 1
openai/whisper-1Industry-leading speech-to-text transcription
FREE
STT
Anthropic
Claude Sonnet 4
anthropic/claude-sonnet-4Balanced Claude with strong coding and reasoning abilities
Context200KMax Output16KInput$3.15/MOutput$15.75/MCache Read$0.32/M|Cache Write$3.94/M
ChatVisionCode
Anthropic
Claude Sonnet 4 (Thinking)
anthropic/claude-sonnet-4-thinkingSonnet 4 with extended thinking for deeper reasoning
Context200KMax Output16KInput$3.15/MOutput$15.75/MCache Read$0.32/M|Cache Write$3.94/M
ChatVisionReasoningCode
Anthropic
Claude Opus 4.6
anthropic/claude-opus-4-6Latest Opus with improved coding and reduced cost
Context200KMax Output32KInput$5.25/MOutput$26.25/MCache Read$0.53/M|Cache Write$6.56/M
ChatVisionReasoningCode
Anthropic
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6Latest Sonnet, top choice for Claude Code and Cursor
Context200KMax Output16KInput$3.15/MOutput$15.75/MCache Read$0.32/M|Cache Write$3.94/M
ChatVisionCode
Anthropic
Claude Haiku 4.5
anthropic/claude-haiku-4-5Fast and capable, great for real-time applications
Context200KMax Output8KInput$1.05/MOutput$5.25/MCache Read$0.10/M|Cache Write$1.31/M
ChatVisionCode
Anthropic
Claude Haiku 3.5
anthropic/claude-haiku-3.5Previous Haiku generation, compact and efficient
Context200KMax Output8KInput$0.84/MOutput$4.20/MCache Read$0.08/M|Cache Write$1.05/M
ChatVisionCode
Anthropic
Claude Sonnet 4.5
anthropic/claude-sonnet-4.5modelsCatalog.modelDesc.anthropic_claude-sonnet-4-5
Context200KMax Output16KInput$3.15/MOutput$15.75/MCache Read$0.32/M|Cache Write$3.94/M
ChatVisionCode
Anthropic
Claude Opus 4.5
anthropic/claude-opus-4.5modelsCatalog.modelDesc.anthropic_claude-opus-4-5
Context200KMax Output32KInput$15.75/MOutput$78.75/MCache Read$1.58/M|Cache Write$19.69/M
ChatVisionReasoningCode
Anthropic
Claude Opus 4.1
anthropic/claude-opus-4.1modelsCatalog.modelDesc.anthropic_claude-opus-4-1
Context200KMax Output32KInput$15.75/MOutput$78.75/MCache Read$1.58/M|Cache Write$19.69/M
ChatVisionReasoningCode
Google
Gemini 2.5 Pro
google/gemini-2.5-proGoogle most capable model with 1M context window
Context1MMax Output66KInput$1.31/MOutput$10.50/M
ChatVisionReasoningCode
Google
Gemini 2.5 Flash
google/gemini-2.5-flashFast Gemini with strong reasoning at low cost
Context1MMax Output66KInput$0.32/MOutput$2.63/M
ChatVisionCode
Google
Gemini 2.0 Flash
google/gemini-2.0-flashPrevious generation flash model, reliable and fast
Context1MMax Output8KInput$0.10/MOutput$0.42/M
ChatVisionCode
Google
Gemini 2.0 Flash Lite
google/gemini-2.0-flash-liteUltra-lightweight model for high-throughput tasks
Context1MMax Output8KInput$0.08/MOutput$0.32/M
ChatVision
Google
Gemini 1.5 Pro
google/gemini-1.5-proProven model with excellent long-context understanding
Context2MMax Output8KInput$1.31/MOutput$5.25/M
ChatVisionCode
Google
Gemini 1.5 Flash
google/gemini-1.5-flashFast and affordable, great for summarization
Context1MMax Output8KInput$0.08/MOutput$0.32/M
ChatVision
DeepSeek
Deepseek Chat
deepseek/deepseek-chatOpen-source powerhouse, strong coding and math skills
Context131KMax Output16KInput$0.29/MOutput$0.44/MCache Read$0.03/M
ChatCode
DeepSeek
Deepseek Reasoner
deepseek/deepseek-reasonerChain-of-thought reasoning model rivaling o1
Context131KMax Output16KInput$0.58/MOutput$2.30/M
ChatReasoningCode
DeepSeek
Deepseek V3.2
deepseek/deepseek-v3.2modelsCatalog.modelDesc.deepseek_deepseek-v3-2
Context131KMax Output66KInput$0.29/MOutput$0.44/M
ChatReasoningCode
DeepSeek
Deepseek V3.1
deepseek/deepseek-v3.1modelsCatalog.modelDesc.deepseek_deepseek-v3-1
Context131KMax Output66KInput$0.29/MOutput$0.44/M
ChatReasoningCode
DeepSeek
Deepseek V3
deepseek/deepseek-v3modelsCatalog.modelDesc.deepseek_deepseek-v3
Context131KMax Output16KInput$0.29/MOutput$1.16/M
ChatCode
DeepSeek
Deepseek R1
deepseek/deepseek-r1modelsCatalog.modelDesc.deepseek_deepseek-r1
Context131KMax Output16KInput$0.58/MOutput$2.30/M
ChatReasoningCode
DeepSeek
Deepseek R1 0528
deepseek/deepseek-r1-0528modelsCatalog.modelDesc.deepseek_deepseek-r1-0528
Context131KMax Output16KInput$0.58/MOutput$2.30/M
ChatReasoningCode
Meta
Llama 4 Maverick
meta/llama-4-maverickLatest Llama with 1M context and multimodal support
Context1MMax Output33KInput$0.28/MOutput$0.89/M
ChatVisionCode
Meta
Llama 4 Scout
meta/llama-4-scoutEfficient Llama 4 variant with 512K context
Context512KMax Output33KInput$0.62/MOutput$0.92/M
ChatVisionCode
Meta
Llama 3.3 70b
meta/llama-3.3-70bStrong open-source model for general tasks
Context128KMax Output8KInput$0.76/MOutput$0.76/M
ChatCode
Meta
Llama 3.1 405b
meta/llama-3.1-405bLargest open-source model, near-frontier performance
Context128KMax Output8KInput$0.68/MOutput$0.84/M
ChatCode
Meta
Llama 3.1 70b
meta/llama-3.1-70bVersatile 70B model with good cost-performance ratio
Context128KMax Output8KInput$0.37/MOutput$0.47/M
ChatCode
Meta
Llama 3.1 8b
meta/llama-3.1-8bLightweight and fast, ideal for simple tasks
Context128KMax Output8KInput$0.19/MOutput$0.19/M
ChatCode
Mistral
Mistral Large
mistral/mistral-largeMistral flagship, strong multilingual and reasoning
Context262KMax Output8KInput$0.53/MOutput$1.58/M
ChatVisionCode
Mistral
Pixtral Large
mistral/pixtral-largeMultimodal model with vision capabilities
Context128KMax Output8KInput$2.10/MOutput$6.30/M
ChatVisionCode
Mistral
Mistral Large 3
mistral/mistral-large-3modelsCatalog.modelDesc.mistral_mistral-large-3
Context131KMax Output8KInput$2.10/MOutput$6.30/M
ChatVisionReasoningCode
Mistral
Devstral 2
mistral/devstral-2modelsCatalog.modelDesc.mistral_devstral-2
Context131KMax Output8KInput$0.53/MOutput$1.58/M
ChatCode
Mistral
Magistral Small
mistral/magistral-smallmodelsCatalog.modelDesc.mistral_magistral-small
Context131KMax Output16KInput$0.10/MOutput$0.32/M
ChatReasoningCode
Mistral
Ministral 14b
mistral/ministral-14bmodelsCatalog.modelDesc.mistral_ministral-14b
Context128KMax Output8KInput$0.19/MOutput$0.19/M
ChatCode
Cohere
Command R Plus
cohere/command-r-plusEnterprise-grade RAG and tool use specialist
Context128KMax Output4KInput$2.63/MOutput$10.50/M
ChatCode
Cohere
Command R
cohere/command-rEfficient model optimized for retrieval tasks
Context128KMax Output4KInput$0.16/MOutput$0.63/M
ChatCode
Cohere
Command A
cohere/command-aLatest Command model with improved reasoning
Context256KMax Output8KInput$2.63/MOutput$10.50/M
ChatCode
xAI
Grok 3
xai/grok-3xAI flagship with deep reasoning and real-time knowledge
Context128KMax Output16KInput$3.15/MOutput$15.75/M
ChatReasoningCode
xAI
Grok 3 Mini
xai/grok-3-miniFast and affordable Grok for everyday tasks
Context128KMax Output16KInput$0.32/MOutput$0.53/M
ChatReasoningCode
xAI
Grok 2
xai/grok-2Previous generation Grok model
Context128KMax Output8KInput$2.10/MOutput$10.50/M
ChatCode
Qwen
Qwen Max
qwen/qwen-maxQwen flagship via direct API
Context32KMax Output8KInput$0.82/MOutput$4.09/M
ChatCode
Qwen
Qwen Plus
qwen/qwen-plusBalanced Qwen model via direct API
Context128KMax Output8KInput$0.42/MOutput$1.26/M
ChatCode
Qwen
Qwen Turbo
qwen/qwen-turboFast Qwen model, deprecated in favor of Qwen Flash
Context128KMax Output8KInput$0.32/MOutput$0.63/M
ChatCode
Qwen
Qwen2.5 Coder 32b
qwen/qwen2.5-coder-32bSpecialized coding model with 32B parameters
Context32KMax Output8KInput$0.21/MOutput$0.63/M
ChatCode
Qwen
Qwen VL Max
qwen/qwen-vl-maxQwen vision-language model via direct API
Context32KMax Output4KInput$2.10/MOutput$6.30/M
ChatVision
Qwen
Qwen3 Max
qwen/qwen3-maxmodelsCatalog.modelDesc.qwen_qwen3-max
Context262KMax Output66KInput$0.37/MOutput$1.47/M
ChatVisionReasoningCode
Qwen
Qwen3.5 Plus
qwen/qwen3.5-plusmodelsCatalog.modelDesc.qwen_qwen3-5-plus
Context1.0MMax Output66KInput$0.12/MOutput$0.70/M
ChatVisionReasoningCode
Qwen
Qwen3.5 Flash
qwen/qwen3.5-flashmodelsCatalog.modelDesc.qwen_qwen3-5-flash
Context1.0MMax Output66KInput$0.03/MOutput$0.22/M
ChatVisionCode
Qwen
Qwen Long
qwen/qwen-longmodelsCatalog.modelDesc.qwen_qwen-long
Context10MMax Output6KInput$0.07/MOutput$0.29/M
Chat
Qwen
Qwq Plus
qwen/qwq-plusmodelsCatalog.modelDesc.qwen_qwq-plus
Context131KMax Output16KInput$0.23/MOutput$0.59/M
ChatReasoningCode
Qwen
Qwen3 Coder Plus
qwen/qwen3-coder-plusmodelsCatalog.modelDesc.qwen_qwen3-coder-plus
Context262KMax Output66KInput$0.59/MOutput$2.31/M
ChatCode
Qwen
Qwen3 VL Plus
qwen/qwen3-vl-plusmodelsCatalog.modelDesc.qwen_qwen3-vl-plus
Context131KMax Output8KInput$0.23/MOutput$0.59/M
ChatVision
Qwen
Qwen Flash
qwen/qwen-flashmodelsCatalog.modelDesc.qwen_qwen-flash
Context1.0MMax Output66KInput$0.03/MOutput$0.29/M
ChatCode
Qwen
Qwen Max Latest
qwen/qwen-max-latestmodelsCatalog.modelDesc.qwen_qwen-max-latest
Context131KMax Output16KInput$0.35/MOutput$1.40/M
ChatCode
Qwen
Qwen Plus Latest
qwen/qwen-plus-latestmodelsCatalog.modelDesc.qwen_qwen-plus-latest
Context131KMax Output16KInput$0.12/MOutput$0.29/M
ChatCode
Qwen
Qwen3 Coder Next
qwen/qwen3-coder-nextmodelsCatalog.modelDesc.qwen_qwen3-coder-next
Context262KMax Output66KInput$0.29/MOutput$2.94/M
ChatCode
Qwen
Qwen VL Plus
qwen/qwen-vl-plusmodelsCatalog.modelDesc.qwen_qwen-vl-plus
Context131KMax Output8KInput$0.12/MOutput$0.59/M
ChatVision
Qwen
Qwen3 Next 80b
qwen/qwen3-next-80bmodelsCatalog.modelDesc.qwen_qwen3-next-80b
Context131KMax Output33KInput$0.37/MOutput$1.47/M
ChatReasoningCode
Qwen
Qwen3 VL 235b
qwen/qwen3-vl-235bmodelsCatalog.modelDesc.qwen_qwen3-vl-235b
Context131KMax Output8KInput$0.59/MOutput$2.31/M
ChatVisionCode
Qwen
Qwen3 Coder 30b
qwen/qwen3-coder-30bmodelsCatalog.modelDesc.qwen_qwen3-coder-30b
Context131KMax Output33KInput$0.21/MOutput$0.63/M
ChatCode
Qwen
Qwen3 32b
qwen/qwen3-32bmodelsCatalog.modelDesc.qwen_qwen3-32b
Context131KMax Output33KInput$0.21/MOutput$0.63/M
ChatReasoningCode
智谱
GLM 5
zhipu/glm-5modelsCatalog.modelDesc.zhipu_glm-5
Context131KMax Output16KInput$1.46/MOutput$4.66/M
ChatReasoningCode
智谱
GLM 4.7
zhipu/glm-4.7modelsCatalog.modelDesc.zhipu_glm-4-7
Context131KMax Output16KInput$0.59/MOutput$2.63/M
ChatReasoningCode
智谱
GLM 4.6
zhipu/glm-4.6modelsCatalog.modelDesc.zhipu_glm-4-6
Context131KMax Output16KInput$0.59/MOutput$2.63/M
ChatReasoningCode
智谱
GLM 4.5
zhipu/glm-4.5modelsCatalog.modelDesc.zhipu_glm-4-5
Context131KMax Output16KInput$0.59/MOutput$2.63/M
ChatReasoningCode
智谱
GLM 4.5 Air
zhipu/glm-4.5-airmodelsCatalog.modelDesc.zhipu_glm-4-5-air
Context131KMax Output16KInput$0.29/MOutput$1.16/M
ChatCode
智谱
GLM 4.7 Flash
zhipu/glm-4.7-flashmodelsCatalog.modelDesc.zhipu_glm-4-7-flash
Context131KMax Output16KInput$0.15/MOutput$0.59/M
ChatCode
MiniMax
Minimax M2.5
minimax/minimax-m2.5modelsCatalog.modelDesc.minimax_minimax-m2-5
Context196KMax Output16KInput$0.30/MOutput$1.26/M
ChatReasoningCode
MiniMax
Minimax M2.1
minimax/minimax-m2.1modelsCatalog.modelDesc.minimax_minimax-m2-1
Context196KMax Output16KInput$0.30/MOutput$1.26/M
ChatCode
MiniMax
Minimax M2
minimax/minimax-m2modelsCatalog.modelDesc.minimax_minimax-m2
Context196KMax Output16KInput$0.23/MOutput$0.93/M
ChatCode
Moonshot
Kimi K2.5
moonshot/kimi-k2.5modelsCatalog.modelDesc.moonshot_kimi-k2-5
Context262KMax Output16KInput$0.59/MOutput$3.05/M
ChatVisionReasoningCode
Moonshot
Kimi K2 Thinking
moonshot/kimi-k2-thinkingmodelsCatalog.modelDesc.moonshot_kimi-k2-thinking
Context131KMax Output16KInput$0.59/MOutput$0.37/M
ChatReasoningCode
豆包
Doubao 1.5 Pro 256k
doubao/doubao-1.5-pro-256kByteDance Doubao with 256K context
Context256KMax Output8KInput$0.58/MOutput$1.16/M
ChatCode
豆包
Doubao 1.5 Pro 32k
doubao/doubao-1.5-pro-32kDoubao Pro with standard 32K context
Context32KMax Output8KInput$0.12/MOutput$0.28/M
ChatCode
豆包
Doubao 1.5 Lite 32k
doubao/doubao-1.5-lite-32kUltra-affordable Doubao for basic tasks
Context32KMax Output8KInput$0.03/MOutput$0.06/M
Chat
Bedrock
Nova Micro
amazon/nova-micromodelsCatalog.modelDesc.amazon_nova-micro
Context128KMax Output4KInput$0.04/MOutput$0.15/M
Chat
Bedrock
Nova Lite
amazon/nova-litemodelsCatalog.modelDesc.amazon_nova-lite
Context300KMax Output4KInput$0.06/MOutput$0.25/M
ChatVision
Bedrock
Nova Pro
amazon/nova-promodelsCatalog.modelDesc.amazon_nova-pro
Context300KMax Output4KInput$0.84/MOutput$3.36/M
ChatVisionCode
Bedrock
Nova Premier
amazon/nova-premiermodelsCatalog.modelDesc.amazon_nova-premier
Context1MMax Output4KInput$2.63/MOutput$13.13/M
ChatVisionReasoningCode
Bedrock
Nemotron Super 3 120b
nvidia/nemotron-super-3-120bmodelsCatalog.modelDesc.nvidia_nemotron-super-3-120b
Context131KMax Output16KInput$0.68/MOutput$2.63/M
ChatReasoningCode
Bedrock
Nemotron Nano 3 30b
nvidia/nemotron-nano-3-30bmodelsCatalog.modelDesc.nvidia_nemotron-nano-3-30b
Context131KMax Output16KInput$0.19/MOutput$0.58/M
ChatCode
Bedrock
Gemma 3 27b
google/gemma-3-27bmodelsCatalog.modelDesc.google_gemma-3-27b
Context128KMax Output8KInput$0.21/MOutput$0.58/M
ChatVisionCode
Bedrock
Gemma 3 12b
google/gemma-3-12bmodelsCatalog.modelDesc.google_gemma-3-12b
Context128KMax Output8KInput$0.10/MOutput$0.29/M
ChatVisionCode
Bedrock
Gemma 3 4b
google/gemma-3-4bmodelsCatalog.modelDesc.google_gemma-3-4b
Context128KMax Output8KInput$0.05/MOutput$0.13/M
ChatVision
Bedrock
Jamba 1.5 Large
ai21/jamba-1.5-largemodelsCatalog.modelDesc.ai21_jamba-1-5-large
Context256KMax Output4KInput$2.10/MOutput$8.40/M
ChatCode
Bedrock
Jamba 1.5 Mini
ai21/jamba-1.5-minimodelsCatalog.modelDesc.ai21_jamba-1-5-mini
Context256KMax Output4KInput$0.21/MOutput$0.42/M
ChatCode
Meta
Llama 3.2 90b
meta/llama-3.2-90bmodelsCatalog.modelDesc.meta_llama-3-2-90b
Context128KMax Output4KInput$2.10/MOutput$2.10/M
ChatVisionCode
Meta
Llama 3.2 11b
meta/llama-3.2-11bmodelsCatalog.modelDesc.meta_llama-3-2-11b
Context128KMax Output4KInput$0.37/MOutput$0.37/M
ChatVision
Meta
Llama 3.2 3b
meta/llama-3.2-3bmodelsCatalog.modelDesc.meta_llama-3-2-3b
Context128KMax Output4KInput$0.16/MOutput$0.16/M
ChatCode
Meta
Llama 3.2 1b
meta/llama-3.2-1bmodelsCatalog.modelDesc.meta_llama-3-2-1b
Context128KMax Output4KInput$0.10/MOutput$0.10/M
Chat
QwenFREE
Flux Merged
qwen/flux-mergedmodelsCatalog.modelDesc.qwen_flux-merged
Context—Max Output—FREE
Image Gen
QwenFREE
Flux Schnell
qwen/flux-schnellmodelsCatalog.modelDesc.qwen_flux-schnell
Context—Max Output—FREE
Image Gen
QwenFREE
Cosyvoice V2
qwen/cosyvoice-v2modelsCatalog.modelDesc.qwen_cosyvoice-v2
Context—Max Output—FREE
TTS
QwenFREE
Sensevoice V1
qwen/sensevoice-v1modelsCatalog.modelDesc.qwen_sensevoice-v1
Context—Max Output—FREE
STT
QwenFREE
Paraformer V2
qwen/paraformer-v2modelsCatalog.modelDesc.qwen_paraformer-v2
Context—Max Output—FREE
STT
amazonFREE
Nova Canvas
amazon/nova-canvasmodelsCatalog.modelDesc.amazon_nova-canvas
Context—Max Output—FREE
Image Gen