Skip to main content

Models

The table below is read live from the platform's model service and stays in sync with the console.

Copy model names directly

When calling the API, copy the value from the Model column below. Case and hyphens must match exactly — typing it by hand invites mistakes.

VendorModelEndpoints
ZhipuOpenAI-compatible
OpenAI-compatible
AnthropicAnthropic, OpenAI-compatible
Anthropic, OpenAI-compatible
Anthropic, OpenAI-compatible
Anthropic, OpenAI-compatible
DeepSeekOpenAI-compatible
OpenAI-compatible
GoogleGemini, OpenAI-compatible
Gemini, OpenAI-compatible
Gemini, OpenAI-compatible
MiniMax Token Plan (minimax.io)OpenAI-compatible
OpenAI-compatible
OpenAI-compatible
MoonshotOpenAI-compatible
OpenAI-compatible
OpenAI-compatible
OpenAI-compatible
OpenAIOpenAI-compatible
OpenAI-compatible
OpenAI-compatible
OpenAI-compatible
OpenAI-compatible, Image generation
xAIOpenAI-compatible
OpenAI-compatible
OpenAI-compatible, Image generation
OpenAI-compatible, Image generation

27 models in total.

Billing​

Pricing varies by model and includes token-based, tiered and per-call billing. Input, output and other applicable rates can differ; check the corresponding model price. Charges are deducted from your paid or complimentary balance. The applicability and deduction order of balances depend on your account rules and billing records.

Per-model rates are authoritative in the console: view model pricing.

Choosing a model​

Use caseWhat to look forWhy
Everyday Q&A / general chatSmall, low-latency, low-cost modelsFast responses, suited to high-frequency conversation
Coding and agentsStrong reasoning and tool-callingHandles code comprehension and multi-turn task execution
Long-document summarizationLong-context modelsBuilt for large text bodies and research material
Structured output / JSONModels with solid OpenAI compatibilityGood for form extraction and automated pipelines
Image generation / editingVerify generation and editing separatelyAn image-generation listing does not establish editing support
Responses APIGPT-series modelsOthers may return not implemented

Checklist before you commit​

  1. Confirm the model exists: copy the name from the table above or /v1/models — don't type it by hand.
  2. Confirm the endpoint matches: see the Endpoints column — chat uses /v1/chat/completions; Claude-style clients use /v1/messages; Gemini uses /v1beta/models/{model}:generateContent.
  3. Confirm parameter support: add advanced parameters one at a time. Don't enable tools, JSON mode, streaming, thinking and image parameters all at once on the first try.
  4. Plan a fallback for production: switch to a backup model on the same protocol when the primary fails, so upstream turbulence doesn't reach your users.