Gemini 3.7 Flash (openai)

This reference documents the ModelFold gateway.

Endpoint

POST /chat/completions

Full URL: https://modelfold.ai/v1/chat/completions

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

ModelFold translates this request to the model provider protocol and returns an OpenAI-style completion. This gateway returns complete JSON responses and does not support stream, tools or upstream-only fields. For coding agents and native protocols, see AI Agent.

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	Allowed values：gemini-3-7-flash-openai。 Example：gemini-3-7-flash-openai。
messages	array<object>	Yes	minItems: 1.
messages[].role	string	Yes	Allowed values：system / user / assistant。 Example：system。
messages[].content	string	Yes	—
max_tokens	integer	No	Default：1024。 Example：1024。
temperature	number	No	—

Request Example

curl -X POST "https://modelfold.ai/v1/chat/completions" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-3-7-flash-openai",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 512
}'

{
  "model": "gemini-3-7-flash-openai",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 512
}

Response

200 — Completed response; usage contains actual token and credit usage.

{
  "ok": true,
  "object": "chat.completion",
  "model": "gemini-3-7-flash-openai",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {}
}