ASI:One Developer Platform

ASI:One is an intelligent AI platform built by Fetch.ai. ASI:One excels at finding the right AI Agents to help you solve everyday tasks involving language, reasoning, analysis, coding, and more.

Developer Quickstart →

Make your first API request in minutes. Learn the basics of the ASI:One platform.

asi1

cURL

curl -X POST https://api.asi1.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ASI_ONE_API_KEY" \
  -d '{
    "model": "asi1",
    "messages": [
      {"role": "user", "content": "Help me plan a trip to Tokyo"}
    ]
  }'

Python

import requests, os

url = "https://api.asi1.ai/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.getenv('ASI_ONE_API_KEY')}"
}
data = {
    "model": "asi1",
    "messages": [{"role": "user", "content": "Help me plan a trip to Tokyo"}]
}

print(requests.post(url, headers=headers, json=data).json())

JavaScript

import OpenAI from 'openai';
import dotenv from 'dotenv';

dotenv.config();

const client = new OpenAI({
  apiKey: process.env.ASI_ONE_API_KEY,
  baseURL: 'https://api.asi1.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'asi1',
  messages: [{ role: 'user', content: 'Help me plan a trip to Tokyo' }],
});

console.log(response.choices[0].message.content);

asi1-ultra

cURL

curl -X POST https://api.asi1.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ASI_ONE_API_KEY" \
  -d '{
    "model": "asi1-ultra",
    "messages": [
      {"role": "user", "content": "Audit this 800-line contract and flag the top five risks"}
    ]
  }'

Python

import requests, os

url = "https://api.asi1.ai/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.getenv('ASI_ONE_API_KEY')}"
}
data = {
    "model": "asi1-ultra",
    "messages": [{"role": "user", "content": "Audit this 800-line contract and flag the top five risks"}]
}

print(requests.post(url, headers=headers, json=data).json())

JavaScript

import OpenAI from 'openai';
import dotenv from 'dotenv';

dotenv.config();

const client = new OpenAI({
  apiKey: process.env.ASI_ONE_API_KEY,
  baseURL: 'https://api.asi1.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'asi1-ultra',
  messages: [
    { role: 'user', content: 'Audit this 800-line contract and flag the top five risks' },
  ],
});

console.log(response.choices[0].message.content);

asi1-mini

cURL

curl -X POST https://api.asi1.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ASI_ONE_API_KEY" \
  -d '{
    "model": "asi1-mini",
    "messages": [
      {"role": "user", "content": "Classify this support ticket as billing, bug, or feature request"}
    ]
  }'

Python

import requests, os

url = "https://api.asi1.ai/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.getenv('ASI_ONE_API_KEY')}"
}
data = {
    "model": "asi1-mini",
    "messages": [{"role": "user", "content": "Classify this support ticket as billing, bug, or feature request"}]
}

print(requests.post(url, headers=headers, json=data).json())

JavaScript

import OpenAI from 'openai';
import dotenv from 'dotenv';

dotenv.config();

const client = new OpenAI({
  apiKey: process.env.ASI_ONE_API_KEY,
  baseURL: 'https://api.asi1.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'asi1-mini',
  messages: [
    { role: 'user', content: 'Classify this support ticket as billing, bug, or feature request' },
  ],
});

console.log(response.choices[0].message.content);

Models

The ASI:One family offers three models that share the same API surface. Pick asi1 for general workloads, asi1-ultra for the deepest reasoning, or asi1-mini for the fastest, lightest responses.

asi1

Adaptive default

Balances reasoning depth, speed, and cost. Activates the right capabilities based on your prompt. Start here.

Best for: general agent workflows, chat, tool calling, mixed workloads.

asi1-ultra

Deepest reasoning

Built for long agentic runs, multi-hop research, and complex code or contract analysis. Up to 500 tool calls per turn.

Best for: long-running tasks, deep research, code audits, agent orchestration.

asi1-mini

Fastest, lightest

Optimized for low-latency interactive workloads. Same 200K context window as the rest of the family with a smaller cost and response footprint.

Best for: real-time chat, classification, autocomplete, simple tool calls, voice.

Key Features

Agentic Reasoning

ASI1 can autonomously plan, execute, and adapt its approach based on evolving inputs and goals.

Natural Language Understanding

ASI1 is highly proficient in understanding and generating human-like text across multiple domains.

Multi-Step Task Execution

Handle complex, goal-oriented tasks without constant user intervention.

Contextual Memory

Retains and utilizes context for longer, more coherent interactions.

API-Driven Integration

Easily embed ASI1 into your applications through a simple, powerful API.

Web3 Native

Designed from the ground up for decentralized environments and blockchain interactions.

Start Building

Chat Completion

Use the API to prompt a model and generate text

Function Calling

Enable models to use external tools and APIs

Image Generation

Create images from text descriptions

Agent Chat Protocol

Enable agents to communicate with each other

Agentic LLM

Call agents from Agentverse for complex tasks

Structured Data

Get model responses that adhere to a JSON schema

OpenAI Compatibility

Use OpenAI SDK with ASI:One