anthropic/claude-opus-4-7Latest flagship, 1M context
deepseek/deepseek-v3.2Open-source flagship, hybrid reasoning
qwen/qwen3.6-plusLatest Qwen flagship
qwen/wan2.7-imageWan image generation
qwen/wan2.7-i2vWan image-to-video
qwen/qwen3-coder-flashFastest code model, lowest cost
qwen/qwen3-coder-480b480B flagship coding model
openai/gpt-5.4-miniReasoning model, 200K context
minimax/minimax-m2.7Reasoning model, 196K context
pixverse/pixverse-v6PixVerse V6, multi-shot video
pixverse/pixverse-c1PixVerse C1, action & effects
qwen/qwen3.5-omni-flashQwen3.5 fast multimodal
qwen/qwen3.5-omni-plusQwen3.5 premium multimodal
qwen/qwen3-vl-flashFast vision, ultra-low cost
vidu/viduq3-proVidu professional video gen
vidu/viduq3-turboVidu fast video, half the cost
anthropic/claude-opus-4-6Flagship, strongest reasoning
anthropic/claude-sonnet-4-6Top choice for Claude Code
google/gemini-3.1-pro-previewReasoning model, 1M context
google/gemini-3.1-flash-image-preview1M context, vision
zhipu/glm-5.1Reasoning model, 131K context
minimax/minimax-m2.5Reasoning model, 196K context
minimax/speech-2.8-hdText-to-speech model
minimax/speech-2.8-turboText-to-speech model
kling/kling-v3-videoKling V3 by Kuaishou, pro video
kling/kling-v3-omni-videoKling V3 Omni, enhanced quality
openai/gpt-5.1Improved reasoning, longer context
xai/grok-4.1-fast-non-reasoningLatest fast model, 256K context
qwen/qwen3.5-plusReasoning model, 1M context
qwen/qwen3.5-flash1M context
qwen/qwen3.5-omniReasoning model, 1M context
qwen/qwen3.5-397bReasoning model, 131K context
zhipu/glm-5Reasoning model, 131K context
zhipu/glm-5-turboReasoning model, 131K context
zhipu/glm-5v-turbo131K context, vision
minimax/minimax-m2.1196K context
moonshot/kimi-k2.5Reasoning model, 262K context
amazon/nova-2-lite300K context, vision
amazon/nova-2-pro300K context, vision
qwen/wan2.7-image-proAlibaba AI model
qwen/wan2.7-t2vAlibaba AI model
qwen/z-image-turboLightweight fast image gen
zhipu/glm-4.7Reasoning model, 131K context
zhipu/glm-4.7-flash131K context
qwen/qvq-maxFlagship visual reasoning
qwen/qvq-plusBalanced visual reasoning
qwen/qwq-plusReasoning-focused Qwen
anthropic/claude-opus-4.5Reasoning model, 200K context
openai/gpt-5Most capable reasoning, 272K context
google/gemini-3-pro-previewReasoning model, 1M context
google/gemini-3-flash-previewReasoning model, 1M context
openai/gpt-5.1-chatReasoning model, 272K context
openai/gpt-5.1-codexReasoning model, 272K context
openai/gpt-5.1-codex-mini200K context
moonshot/kimi-k2-thinkingReasoning model, 131K context
mistral/mistral-large-3Reasoning model, 131K context
xai/grok-4.1-fastReasoning model, 256K context
amazon/nova-embed-multimodalText embedding model
azure/flux-2-proAzure OpenAI AI model
qwen/qwen-math-plusSpecialized math reasoning
qwen/qwen-math-turboFast math reasoning, lower cost
minimax/minimax-m2196K context
anthropic/claude-haiku-4-5Ultra-fast, lowest cost
openai/gpt-4o-transcribe-diarizeTranscription with speaker diarization
google/veo-3.1Google AI model
google/veo-3.1-fastGoogle AI model
google/veo-3.1-liteGoogle AI model
qwen/wan2.6-i2vWan image-to-video standard
qwen/wan2.6-i2v-flashWan Flash, lower price
openai/gpt-5-proReasoning model, 272K context
azure/mai-image-2Azure OpenAI AI model
qwen/wan2.6-t2vAlibaba AI model
qwen/qwen-omni-turboOmni understanding: text+image+audio
zhipu/glm-4.6Reasoning model, 131K context
anthropic/claude-sonnet-4.5Reasoning model, 200K context
qwen/qwen3-vl-plus131K context, vision
qwen/qwen3-coder-next262K context
qwen/qwen3-vl-235b131K context, vision
xai/grok-4-fastReasoning model, 256K context
xai/grok-4-fast-non-reasoningFast responses, 256K context
openai/gpt-5-codexReasoning model, 272K context
qwen/qwen3-next-80bReasoning model, 131K context
qwen/qwen3-maxReasoning model, 262K context
nvidia/nemotron-super-3-120bReasoning model, 131K context
nvidia/nemotron-nano-3-30b131K context
qwen/qwen-vl-ocrProfessional OCR extraction
qwen/qwen-mt-plusProfessional machine translation
qwen/qwen-mt-turboFast translation, lower cost
google/gemini-2.5-flash-image1M context, vision
deepseek/deepseek-v3.1Reasoning model, 131K context
openai/gpt-5-chatReasoning model, 272K context
openai/gpt-5-miniReasoning model, 200K context
openai/gpt-5-nano200K context, vision
anthropic/claude-opus-4.1Reasoning model, 200K context
openai/gpt-oss-120b128K context
openai/gpt-oss-20b128K context
qwen/qwen-image-edit-plusAI-powered image editing
qwen/qwen-image-edit-maxPremium image editing
qwen/qwen-flash1M context
zhipu/glm-4.5Reasoning model, 131K context
zhipu/glm-4.5-air131K context
qwen/qwen3-coder-plus262K context
qwen/qwen3-coder-30b131K context
mistral/voxtral-smallSpeech-to-text model
mistral/voxtral-miniSpeech-to-text model
google/gemini-embedding-001Text embedding model
mistral/devstral-2131K context, vision
mistral/magistral-smallReasoning model, 131K context
azure/flux-kontext-proAzure OpenAI AI model
twelvelabs/marengo-embed-3.0Text embedding model
qwen/qwen-image-2.0Qwen text-to-image, standard
qwen/qwen-image-2.0-proQwen text-to-image, pro
qwen/qwen-image-maxQwen text-to-image, best quality
deepseek/deepseek-r1-0528Reasoning model, 131K context
anthropic/claude-sonnet-4-thinkingReasoning model, 200K context
google/imagen-4.0Google AI model
google/imagen-4.0-fastGoogle AI model
google/imagen-4.0-ultraGoogle AI model
microsoft/phi-4-reasoningReasoning model, 16K context
writer/palmyra-x5128K context
qwen/qwen3-32bReasoning model, 131K context
google/gemini-2.5-flashLightning fast, 1M context
google/gemini-2.5-flash-liteLowest cost Gemini
openai/o3Reasoning model, 200K context
openai/o4-miniCompact reasoning with tools
cohere/embed-v4Text embedding model
openai/gpt-4.1200K context flagship
openai/gpt-4.1-miniFast balanced, best value
openai/gpt-4.1-nanoUltra-fast, lowest cost
amazon/nova-sonicText-to-speech model
meta/llama-4-maverick1M context, vision
meta/llama-4-scout512K context, vision
mistral/ministral-14b128K context
amazon/nova-premierReasoning model, 1M context
google/gemini-2.5-pro1M context, deep reasoning
openai/gpt-4o-mini-ttsGPT-4o Mini TTS β expressive, natural speech
openai/gpt-4o-transcribeGPT-4o transcription β more accurate than Whisper
openai/gpt-4o-mini-transcribeFast and affordable transcription
cohere/command-a256K context
google/gemma-3-27b128K context, vision
google/gemma-3-12b128K context, vision
google/gemma-3-4b128K context, vision
microsoft/phi-4-mini16K context
microsoft/phi-4-multimodal16K context, vision
xai/grok-3Reasoning model, 128K context
xai/grok-3-miniReasoning model, 128K context
amazon/nova-reel-1.1Amazon AI model
qwen/qwen-max-latest131K context
qwen/qwen-plus-latest131K context
doubao/doubao-1.5-pro-256k256K context
doubao/doubao-1.5-pro-32k32K context
doubao/doubao-1.5-lite-32k32K context
deepseek/deepseek-reasonerFocused deep reasoning
deepseek/deepseek-r1Reasoning model, 131K context
mistral/codestral256K context
qwen/cosyvoice-v2Text-to-speech model
deepseek/deepseek-v3131K context
microsoft/phi-416K context
meta/llama-3.3-70b128K context
amazon/nova-micro128K context
amazon/nova-lite300K context, vision
amazon/nova-pro300K context, vision
amazon/nova-reel-1.0Amazon AI model
cohere/rerank-3.5Document reranking
mistral/mistral-large262K context
mistral/pixtral-large128K context, vision
qwen/qwen2.5-coder-32b32K context
writer/palmyra-vision128K context, vision
openai/gpt-4o-audio-previewSpeech-to-text model
meta/llama-3.2-90b128K context, vision
meta/llama-3.2-11b128K context, vision
meta/llama-3.2-3b128K context
meta/llama-3.2-1b128K context
qwen/qwen-max32K context
qwen/qwen-plus128K context
qwen/qwen-turbo128K context
qwen/qwen-long10M context
writer/palmyra-x4128K context
cohere/command-r-plus128K context
cohere/command-r128K context
qwen/qwen-vl-max32K context, vision
qwen/qwen-vl-plus131K context, vision
ai21/jamba-1.5-large256K context
ai21/jamba-1.5-mini256K context
xai/grok-2128K context
meta/llama-3.1-405b128K context
meta/llama-3.1-70b128K context
meta/llama-3.1-8b128K context
openai/gpt-4o-mini128K context, vision
qwen/sensevoice-v1Speech-to-text model
openai/gpt-4o128K context, vision
amazon/titan-embed-text-v2Text embedding model
openai/text-embedding-3-smallText embedding model
openai/text-embedding-3-largeText embedding model
qwen/paraformer-v2Speech-to-text model
openai/tts-1Standard text-to-speech
openai/tts-1-hdText-to-speech model
cohere/embed-multilingual-v3Text embedding model
openai/whisper-1Speech-to-text model
openai/text-embedding-ada-002Text embedding model
openai/gpt-5.4-nanoGPT-5.4 Nano β ultra-fast, low-latency for classification, extraction, and sub-agents
openai/gpt-5.3-chatGPT-5.3 Chat β previous generation flagship chat model
google/gemini-3-pro-image-previewGemini 3 Pro Image β highest quality image generation & editing, up to 4K
google/gemini-3.1-flash-lite-previewGemini 3.1 Flash Lite β ultra-low cost for high-throughput tasks
qwen/qwen3-tts-flashQwen3 TTS Flash β fast text-to-speech with natural voice
qwen/qwen3-tts-instruct-flashQwen3 TTS Instruct β instruction-controlled speech synthesis
google/lyria-3-pro-previewLyria 3 Pro β full-length AI music generation by Google DeepMind
google/lyria-3-clip-previewLyria 3 Clip β 30-second AI music clips by Google DeepMind
anthropic/claude-sonnet-4Reasoning model, 200K context
deepseek/deepseek-chat131K context
anthropic/claude-haiku-3.5200K context, vision