Gemini / Vertex

Behavior

URL-encode the public model name in the path. Also supports :streamGenerateContent and :countTokens. Vertex uses /vertex/v1/models/{model} with the same operation suffixes. Provider OAuth credentials stay in deployment settings.

Endpoint and authentication

POST /v1beta/models/YOUR_MODEL_NAME:generateContent

Use an XHub API key: Authorization: Bearer . Do not use upstream provider credentials as gateway keys.

Use the gateway root Base URL shown in the playground, without appending /v1; send requests to the full endpoint path above.

Request example

curl "$XHUB_BASE_URL/v1beta/models/YOUR_MODEL_NAME:generateContent" \
  -H "Authorization: Bearer $XHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents":[{"role":"user","parts":[{"text":"Hello, introduce yourself."}]}]}'

Request parameters

Field	Type	Description
contents	object[] · required	role and parts with text or supported media.
generationConfig / tools	object / array	Generation settings and tool declarations.

Success response

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Hello!"
          }
        ]
      }
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 10,
    "candidatesTokenCount": 5
  }
}

Field	Type
candidates	object[]
candidates[].content	object
candidates[].content.role	string
candidates[].content.parts	object[]
candidates[].content.parts[].text	string
usageMetadata	object
usageMetadata.promptTokenCount	number
usageMetadata.candidatesTokenCount	number

Errors and troubleshooting

HTTP	Meaning
400	Invalid request. Check JSON, parameters and query.
401	Missing or invalid XHub credential.
403	Permission denied. Check model scope or policy.
429	Limit exceeded. Inspect response details and Retry-After.