Models
Use documented model IDs in requests. Aliases are accepted for common model names, but exact IDs are best for automation and reproducible routing.
Claude, Opus 5, and Fable 5
Claude models use Anthropic-compatible routes. Opus 5 follows the current Opus routing policy, while Fable 5 uses its Anthropic-compatible ID and OpenAI-backed route.
| Model | Family | Endpoints |
|---|---|---|
anthropic/claude-opus-5.5 | Opus 5.5 | /v1/messages, /v1/chat/completions |
anthropic/claude-opus-5 | Opus 5 | /v1/messages, /v1/chat/completions |
anthropic/claude-sonnet-5 | Sonnet 5 | /v1/messages, /v1/chat/completions |
anthropic/claude-haiku-4.5 | Haiku 4.5 | /v1/messages, /v1/chat/completions |
anthropic/fable-5 | Fable 5 | /v1/messages, /v1/chat/completions, /v1/responses |
GPT
GPT models use OpenAI provider routes and are available through OpenAI-compatible endpoints.
| Model | Family | Endpoints |
|---|---|---|
openai/gpt-6.1-sol | GPT-6.1 Sol | /v1/chat/completions, /v1/responses |
openai/gpt-6-sol | GPT-6 Sol | /v1/chat/completions, /v1/responses |
openai/gpt-6-astra | GPT-6 Astra | /v1/chat/completions, /v1/responses |
openai/gpt-6-luna | GPT-6 Luna | /v1/chat/completions, /v1/responses |
Open model groups
Open model-group IDs route through the configured external/open provider paths for the matching route.
| Model | Family |
|---|---|
z-ai/glm-5.3 | GLM 5.3 |
z-ai/glm-5.3-flash | GLM 5.3 Flash |
z-ai/glm-5.2 | GLM 5.2 |
z-ai/glm-5-turbo | GLM 5 Turbo |
minimax/minimax-m3 | MiniMax M3 |
deepseek/deepseek-v4-pro | DeepSeek V4 Pro |
deepseek/deepseek-v4-flash | DeepSeek V4 Flash |
Endpoint compatibility
| Endpoint | Supported families |
|---|---|
/v1/messages | Claude, Opus 5, Fable 5, open model groups |
/v1/chat/completions | Claude, Opus 5, Fable 5, GPT, open model groups |
/v1/responses | Fable 5, GPT, open model groups |
/v1/models | All documented models available to the authenticated key |