Catalog

20 models, one endpoint

From frontier flagship models to fine-tuned open weights. Sorted by latency, price, or context length — pick what fits your workload.

ModelProviderContextInput / 1MOutput / 1MP50 latencyModalities
GPT-5
Featured
openai/gpt-5
OpenAI400K$5.00$15.00480ms
textvisioncode
GPT-5 Mini
Featured
openai/gpt-5-mini
OpenAI200K$0.60$2.40220ms
textvision
Claude Opus 4.7
Featured
anthropic/claude-opus-4.7
Anthropic1M$15.00$75.00920ms
textvisioncode
Claude Sonnet 4.6
Featured
anthropic/claude-sonnet-4.6
Anthropic500K$3.00$15.00410ms
textvisioncode
Gemini 2.5 Pro
Featured
google/gemini-2.5-pro
Google2M$1.25$10.00520ms
textvisionaudiocode
DeepSeek V4
Featured
deepseek/deepseek-v4
DeepSeek128K$0.14$0.28290ms
textcode
GPT-4o
openai/gpt-4o
OpenAI128K$2.50$10.00380ms
textvisionaudio
Claude Haiku 4.5
anthropic/claude-haiku-4.5
Anthropic200K$0.80$4.00180ms
textvision
Gemini 2.5 Flash
google/gemini-2.5-flash
Google1M$0.08$0.30160ms
textvision
Llama 4 405B
meta/llama-4-405b
Meta256K$2.70$2.70680ms
textcode
Llama 4 70B Instruct
meta/llama-4-70b
Meta128K$0.55$0.65240ms
textcode
DeepSeek R2
deepseek/deepseek-r2
DeepSeek128K$0.55$2.191450ms
textcode
Qwen3 Max
alibaba/qwen3-max
Alibaba1M$1.60$6.40540ms
textvisioncode
Qwen3 72B Instruct
alibaba/qwen3-72b
Alibaba256K$0.40$1.20270ms
textcode
Mistral Large 2
mistral/mistral-large-2
Mistral128K$2.00$6.00350ms
textcode
Mistral Small 3.1
mistral/mistral-small-3.1
Mistral128K$0.20$0.60200ms
textvision
Grok 4
xai/grok-4
xAI256K$5.00$15.00520ms
textvision
Grok 4 Mini
xai/grok-4-mini
xAI128K$0.30$0.50190ms
text
Command R+ v2
cohere/command-r-plus-2
Cohere256K$2.50$10.00410ms
text
Yi Large 2
01-ai/yi-large-2
01.AI200K$0.70$2.00320ms
text