API Endpoints

The TokOne gateway exposes OpenAI-, Anthropic-, and Gemini-compatible protocols at once. This page lists the endpoints actually available.

Common configuration

Item	Value
Base URL	https://api.tokone.ai (use your deployment domain)
Auth header	Authorization: Bearer <key> / x-api-key: <key> / x-goog-api-key: <key>
Content type	application/json
Streaming	add "stream": true; response is text/event-stream

Most endpoints are also available as a root-path alias without the prefix (e.g. /chat/completions); prefer the /v1 form.

OpenAI-compatible endpoints

Method	Path	Notes
POST	/v1/chat/completions	Chat Completions
POST	/v1/embeddings	Text embeddings (only when the key's group platform is OpenAI)
POST	/v1/responses	OpenAI Responses API
GET	/v1/models	Model list
GET	/v1/usage	Usage query

Request/response shapes match OpenAI's, so point the official SDK's base_url at TokOne and go.

Anthropic-compatible endpoints

Method	Path	Notes
POST	/v1/messages	Claude Messages API
GET	/v1/models	Model list

Example:

curl https://api.tokone.ai/v1/messages \
  -H "x-api-key: $TOKONE_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-6",
    "max_tokens": 512,
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Gemini-compatible endpoints

Native Gemini style under /v1beta, with model:action in the path:

Method	Path	Notes
GET	/v1beta/models	Model list
GET	/v1beta/models/:model	Single model info
POST	/v1beta/models/{model}:generateContent	Generate content
POST	/v1beta/models/{model}:streamGenerateContent	Streaming generation

Example:

curl "https://api.tokone.ai/v1beta/models/gemini-3.5-flash:generateContent" \
  -H "x-goog-api-key: $TOKONE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{ "parts": [{ "text": "Hello" }] }]
  }'

Error codes

TokOne follows the standard HTTP status codes of each compatible protocol:

Status	Meaning	Common cause
400	Bad request	Missing/malformed params; key sent via query param
401	Unauthorized	API key missing, wrong, or disabled
402	Insufficient balance	Not enough balance for this call
404	Endpoint/model unavailable	Wrong path, or endpoint not applicable to the key's platform group
429	Rate limited	Too many requests, retry later
5xx	Upstream/gateway error	Upstream temporarily unavailable, retry

Client examples

Point any OpenAI-compatible SDK's base_url at https://api.tokone.ai/v1 and set api_key to your sk- key — see Quick Start.