Request and response library

Create chat completion

POST

/v1/chat/completions

Request

Creates a model response for the given chat conversation.

Name
model
Type
string
Required
required
Description
ID of the model to use
Name
messages
Type
object[]
Required
required
Description
A list of messages comprising the conversation so far.
- Name
  role
  Type
  string
  Required
  required
  Description
  The role of the author of this message.
- Name
  content
  Type
  string
  Required
  required
  Description
  The contents of the message.
Name
temperature
Type
double
Required
required
Description
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic
Name
stream
Type
boolean
Required
required
Description
If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message
Name
max_tokens
Type
int64
Required
required
Description
The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

Responses

Returns a response with fields like model, id, and conversation_id for identification, thought explaining reasoning, choices containing the generated message, and usage tracking token consumption.

Curl

curl -X POST \
  -H "Authorization: bearer <your token here>" -H "Content-Type: application/json" \
  "https://api.asi1.ai/v1/chat/completions" \
  -d '{
  "model": "asi1-mini",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "temperature": 0.7,
  "stream": false,
  "max_tokens": 1024
}'

HTTP 200

{
  "model": "asi1-mini",
  "id": "id_kKg27rnGyfH4NknTL",
  "executable_data": [],
  "conversation_id": null,
  "thought": [
    "The user has initiated a simple greeting. This is a standard conversational start, and my response should be polite and professional, introducing myself as ASI1-Mini while highlighting my unique capabilities as an agentic, decentralised-focused model."
  ],
  "tool_thought": [],
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "Hello! I'm ASI1-Mini, an advanced agentic and decentralised-focused assistant powered by fetch.ai Inc. I'm designed to support complex workflows with executable expertise. How can I assist you today?"
      }
    }
  ],
  "usage": {
    "prompt_tokens": 39,
    "completion_tokens": 100,
    "total_tokens": 139
  }
}