OpenAIOfficial
GPT-6 Astra
openai/gpt-6-astra
OpenAI's new flagship — the strongest reasoning, coding, and agentic model in the GPT line.
OpenAI ChatResponses
Usage842.29MStability91.67%
Model routing
Use OpenAI-compatible and Anthropic-compatible protocols with one key, one base URL, and one billing account.
34 models
openai/gpt-6-astra
OpenAI's new flagship — the strongest reasoning, coding, and agentic model in the GPT line.
openai/gpt-5.6-sol
OpenAI's flagship GPT-5.6 for the hardest reasoning, coding, and agentic work.
openai/gpt-5.6-terra
Balanced GPT-5.6 quality and cost for production workloads.
openai/gpt-5.6-luna
The most efficient GPT-5.6 for high-volume and latency-sensitive work.
openai/gpt-5.5
OpenAI GPT-5.5 — flagship, 1M context, top reasoning & agentic coding.
openai/gpt-image-2.5-sunburst
OpenAI GPT Image 2.5 Sunburst — most capable image generation & editing.
anthropic/claude-opus-5
Anthropic's current flagship Opus — a step change on agentic coding and long-horizon work.
anthropic/claude-sonnet-5
Anthropic's most agentic Sonnet — Opus-class capability at lower cost.
anthropic/claude-fable-5
Anthropic's most powerful model — Mythos-class, above Opus.
openai/gpt-image-2.5-flare
OpenAI GPT Image 2.5 Flare — fastest high-quality image generation & editing.
minimax/minimax-m3
minimax/minimax-m2.7
openai/gpt-image-2
OpenAI GPT Image 2 — high-fidelity image generation & editing.
minimax/minimax-m2.7-highspeed
minimax/minimax-hailuo-2.3
MiniMax Hailuo 2.3 — high-quality text-to-video, 6 / 10 sec, up to 1080P.
minimax/minimax-hailuo-2.3-fast
MiniMax Hailuo 2.3 Fast — faster generation at lower cost.
moonshot/kimi-k3
Moonshot's open-weight flagship — 2.8T MoE, 1M context, native vision, always-on reasoning.
zhipu/glm-5.2
Zhipu GLM-5.2 — flagship 1M-context MoE for long-horizon coding.
anthropic/claude-opus-4.8
Anthropic Claude Opus 4.8 — current flagship, top reasoning & coding.
anthropic/claude-sonnet-4.6
Anthropic Claude Sonnet 4.6 — best price-to-quality balance.
anthropic/claude-haiku-4.5
Anthropic Claude Haiku 4.5 — cheapest current-gen, fast.
google/gemini-3-pro-image
Nano Banana Pro — Google's most advanced Gemini 3 Pro image generation and editing.
google/gemini-3.1-flash-image
Nano Banana 2 — current default Gemini image model.
google/gemini-3.1-flash-lite-image
Nano Banana 2 Lite — the fastest, cheapest Nano Banana, about 4 seconds per 1K image.
google/gemini-3.1-flash-lite
Gemini 3.1 Flash-Lite — Google's most cost-efficient model for high-volume tasks.
google/gemini-3-flash-preview
Gemini 3 Flash Preview — next-gen Flash speed and cost, multimodal input.
google/gemini-3.5-flash
Gemini 3.5 Flash — near-flagship intelligence at Flash speed and cost.
google/gemini-2.5-flash-image
Nano Banana — fast Gemini image generation and editing.
google/gemini-2.5-pro
Gemini 2.5 Pro — Google flagship, 1M context, strong reasoning & coding.
google/gemini-3.1-pro-preview
Gemini 3.1 Pro — Google flagship for advanced math, code, and reasoning.
deepseek/deepseek-v4-flash
DeepSeek V4 Flash — fast, cheapest V4, thinking + non-thinking modes.
deepseek/deepseek-v4-pro
DeepSeek V4 Pro — flagship reasoning model, 1M context, ultra-low cost.
anthropic/claude-opus-4.7
Anthropic Claude Opus 4.7 — top-tier reasoning, coding, agentic work.
anthropic/claude-opus-4.6
Anthropic Claude Opus 4.6 — previous-gen Opus, same price as 4.7/4.8.