Skip to main content
POST
/
v1
/
chat
/
completions
Chat completions
curl --request POST \
  --url https://api.gately.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello, how are you today?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 150
}
'

Documentation Index

Fetch the complete documentation index at: https://docs.gately.ai/llms.txt

Use this file to discover all available pages before exploring further.

Chat Completions API

The Chat Completions API allows you to have dynamic conversations with AI models. This endpoint enables you to send a series of messages and receive AI-generated responses that maintain context throughout the conversation.

Features

  • Support for multiple advanced AI models
  • Streaming responses for real-time applications
  • Temperature and other control parameters
  • Function calling capabilities

Example Usage

Models

Available models for chat completions:
  • wizardlm-2-7b
  • claude-3-5-sonnet
  • gpt-4o-mini

Example Request

{
  "stream": false,
  "model": "wizardlm-2-7b",
  "messages": [
    {
      "role": "user",
      "content": "What is artificial intelligence?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1500
}

Example With Function Calling

{
  "stream": false,
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "What's the weather like in New York?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location"]
        }
      }
    }
  ]
}

Example With Image Recognition

{
  "stream": false,
  "model": "claude-3-5-sonnet",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What's in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/image.jpg",
            "detail": "auto"
          }
        }
      ]
    }
  ]
}

Authorizations

Authorization
string
header
required

Enter your API key prefixed with 'Bearer '

Body

application/json
model
string
required
messages
object[]
required
temperature
number
max_tokens
integer
stream
boolean
default:false

Whether to stream the response

Response

200

Successful response