API Reference

OverviewCopy Anchor Link

TokenLab supports OpenAI-compatible endpoints plus Anthropic and Gemini request formats. Existing OpenAI clients can use /v1; choose another format only when your application needs behavior specific to that API. POST /v1/responses is optional and depends on model support.

Base URLCopy Anchor Link

https://api.tokenlab.sh

AuthenticationCopy Anchor Link

Model requests use a TokenLab API key. The standard authentication header is:

Authorization: Bearer sk-your-api-key

GET /v1/models, GET /v1/models/{model}, and GET /v1/pricing are public and need no key. Anthropic Messages also accepts x-api-key; Gemini accepts x-goog-api-key or ?key= as well as Bearer authentication. /v1/management/* requires a management token (mt-...).

Get your API key from the Console.

Delivery policyCopy Anchor Link

Generation requests accept X-TokenLab-Delivery-Policy: auto | verified | official. A request header overrides the API key setting, which overrides the Workspace default.

• Auto uses TokenLab Verified when available, then Official if needed. You pay for the option that completes your request.
• TokenLab Verified is delivery verified by TokenLab. The Verified price applies.
• Official bills the Official price, which is the model maker's published price.
• Realtime sessions use the API key or Workspace setting and do not accept a query-string override.

An invalid header returns 400. If the requested option is unavailable, TokenLab returns 503 delivery_tier_unavailable and a request ID. Read retryable: when the selected operation has no supply, it is false. Do not repeat the same request unchanged.

Supported EndpointsCopy Anchor Link

Chat & Text GenerationCopy Anchor Link

Embeddings & RerankCopy Anchor Link

DecisionsCopy Anchor Link

ImagesCopy Anchor Link

AudioCopy Anchor Link

RealtimeCopy Anchor Link

VideoCopy Anchor Link

Async TasksCopy Anchor Link

MusicCopy Anchor Link

3D GenerationCopy Anchor Link

ModelsCopy Anchor Link

Gemini (v1beta)Copy Anchor Link

Native Google Gemini API format support:

Response FormatCopy Anchor Link

Each endpoint preserves its API format. The success and error examples below use Chat Completions format.

Success ResponseCopy Anchor Link

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "gpt-5.6-terra",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "Hello!"}, "finish_reason": "stop"}],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Request identifiersCopy Anchor Link

Official request rejections may include upstream with the service’s reported error and public service name. Private delivery details and credentials are not part of the public response contract. See Handle API errors. Use the public headers below when they are present.

Error ResponseCopy Anchor Link

{
  "error": {
    "message": "Invalid API key provided",
    "type": "invalid_api_key",
    "code": "invalid_api_key"
  }
}

Rate LimitsCopy Anchor Link

Rate limits are role-based and configurable by administrators. Default values:

When rate limits are exceeded, the API returns a 429 status code with a Retry-After header indicating how long to wait.

OpenAPI SpecificationCopy Anchor Link