TokenLink — AI Model API Relay Platform

Google Gemini generateContent API, compatible with Gemini CLI and the Gemini SDK

TokenLink provides a Gemini generateContent API-compatible endpoint that Gemini CLI and the Google AI SDK can use directly.

Connectivity check

GET /gemini

curl https://tokenlink.stelarx.ai/gemini
# {"status": "ok"}

Generate content

POST /gemini/v1beta/models/{model}:{action}

Non-streaming request

curl "https://tokenlink.stelarx.ai/gemini/v1beta/models/gemini-2.5-flash:generateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -d '{
    "contents": [{
      "parts": [{"text": "Explain the basic principles of quantum computing"}]
    }]
  }'

Streaming request

curl "https://tokenlink.stelarx.ai/gemini/v1beta/models/gemini-2.5-flash:streamGenerateContent" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: YOUR_API_KEY" \
  -d '{
    "contents": [{
      "parts": [{"text": "Write a quicksort implementation in Python"}]
    }],
    "generationConfig": {
      "temperature": 0.7,
      "maxOutputTokens": 2048
    }
  }'

URL parameters

Parameter	Description	Example
`model`	Model ID	`gemini-2.5-flash`
`action`	Action type	`generateContent` or `streamGenerateContent`

Response

{
  "candidates": [{
    "content": {
      "role": "model",
      "parts": [{"text": "Quantum computing is a..."}]
    },
    "finishReason": "STOP"
  }],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 150,
    "totalTokenCount": 160
  },
  "modelVersion": "gemini-2.5-flash"
}

List models (Gemini format)

GET /gemini/v1beta/models

Returns a model list in Gemini format, used for Gemini CLI's model discovery.

curl https://tokenlink.stelarx.ai/gemini/v1beta/models \
  -H "x-goog-api-key: YOUR_API_KEY"

Note: TokenLink performs format conversion for non-Gemini models. See Protocol Adaptation for details.