POST
/
v1
/
chat
/
completions
Chat Compatible Thinking
curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "reasoning_effort": "<string>",
  "temperature": 123,
  "top_p": 123,
  "max_tokens": 123,
  "stream": true
}
'
{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {}
  ],
  "usage": {}
}
Official documentation: https://ai.google.dev/gemini-api/docs/text-generation
Use Gemini models with thinking/reasoning capabilities through the standard OpenAI Chat Completions API format.

​
Overview

This endpoint enables Gemini’s thinking mode through the OpenAI-compatible chat format. By adding the reasoning_effort parameter, you can control how much reasoning the model performs before responding.

​
Authentication

All requests require a Bearer token in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

​
model
string
required
The Gemini model ID. For example: gemini-2.5-pro, gemini-2.5-flash.
​
messages
array
required
A list of messages comprising the conversation.
​
reasoning_effort
string
Controls the thinking effort level. Values: low, medium, high.
​
temperature
number
default:"1"
Sampling temperature between 0 and 2.
​
top_p
number
default:"1"
Nucleus sampling parameter.
​
max_tokens
integer
Maximum number of tokens to generate.
​
stream
boolean
default:"false"
Whether to stream responses.

​
Request Example

curl -X POST https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-pro",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ],
    "temperature": 0.1,
    "top_p": 1.0,
    "stream": true,
    "reasoning_effort": "low"
  }'

​
Response Example

{
  "id": "chatcmpl-gemini-think-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gemini-2.5-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 8,
    "total_tokens": 18
  }
}

​
Response Fields

​
id
string
Unique identifier for the completion.
​
object
string
Object type, which is chat.completion.
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model used.
​
choices
array
List of completion choices.
​
usage
object
Usage statistics for the request.

​
Reasoning Effort Levels

LevelDescription
lowMinimal thinking, faster responses
mediumBalanced thinking and speed
highMaximum reasoning depth

​
Available Models

  • gemini-2.5-pro
  • gemini-2.5-flash