Models
Put the model name from the tables below into the model field of your request body. You can switch models on the same endpoint at any time. The tables list the models the gateway currently offers; actual availability depends on your account in the console.
Query Models in Real Time
Call GET /v1/models (with your key) at any time to get the list of models your key can currently access.
Anthropic Claude
Supports both the OpenAI-compatible protocol (/v1/chat/completions) and the Claude-native protocol (/v1/messages). Prompt caching (including 1h TTL), tools, and vision are supported.
| Model | Notes |
|---|
claude-fable-5 | Fable 5, strongest flagship |
claude-opus-5 | Opus 5 flagship |
claude-sonnet-5 | Sonnet 5, balanced speed and quality |
claude-opus-4-8 / -4-7 / -4-6 | Opus 4.x series |
claude-sonnet-4-6 | Sonnet 4.6 |
claude-haiku-4-5 | Haiku, lightweight and fast |
OpenAI GPT
| Model | Notes |
|---|
gpt-5.6-sol | GPT-5.6 flagship tier |
gpt-5.6-terra | GPT-5.6 balanced tier |
gpt-5.6-luna | GPT-5.6 light tier for everyday tasks |
gpt-5.5 | General-purpose chat |
gpt-5.4 / gpt-5.4-mini | General-purpose chat, different tiers |
Zhipu GLM
| Model | Notes |
|---|
glm-5.2 / glm-5.1 | GLM 5 series |
DeepSeek
| Model | Notes |
|---|
deepseek-v4-pro | High performance |
deepseek-v4-flash | Lightweight and fast |
Kimi
| Model | Notes |
|---|
kimi-k3 | K3 flagship |
kimi-k2.7-code | Code-focused |
kimi-k2.6 | General-purpose chat |
MiniMax
| Model | Notes |
|---|
minimax-m3 / minimax-m2.7 / minimax-m2.5 | M series |
xAI Grok
| Model | Notes |
|---|
grok-4.5 | Flagship chat |
grok-4.3 | General-purpose chat |
grok-4.20-0309-reasoning / -non-reasoning | 4.20 reasoning / non-reasoning tiers |
grok-4.20-multi-agent-0309 | Multi-agent |
grok-build-0.1 | Build / code |
grok-imagine-image / -image-quality | Image generation (per image) |
grok-imagine-video | Video generation (per second) |
Google Gemini
OpenAI-compatible calls use the table below; for the native protocol see Gemini Native.
| Model | Notes |
|---|
gemini-3.1-pro-preview | Pro preview |
gemini-3-pro-preview / gemini-3-flash-preview | 3-series previews |
gemini-2.5-pro | 2.5 Pro |
gemini-2.5-flash | 2.5 Flash |
Image Generation
Called via the Images endpoint, billed per image.
| Model | Notes |
|---|
gpt-image-2 | Image generation, billed by actual output resolution |
grok-imagine-image / -image-quality | Grok image generation |
Pricing
For real-time pricing, see the Model Square on our website, or the pricing page in your console.