Pareto API

Q: What is the Pareto model ID?

Use unbiased/pareto as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Pareto is Unbiased's composite model: it runs several models against the same request and returns the best answer, with a 262K context window and image input.

Modalities: Image, TextText
In / Out price: $2.65/$7.93per 1M
Context window: 256K tokens
Released: Sep 17, 2026

Pareto overview

Pareto by Unbiased

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Pareto specs

Model ID: unbiased/pareto
Developer: Unbiased
Context window: 262,144 tokens
Max output: 131,072 tokens
Input: Image, Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is Pareto API?

Pareto is a multimodal composite model from Unbiased. Rather than being a single set of weights, it runs several models against the same request and returns the best answer, without switching mid-conversation, which is what lets prompt caching keep working across turns.

Unbiased positions it for research, coding and agentic workflows, with frontier-level quality across general-purpose tasks at a fraction of frontier cost. Pareto and the Unbiased platform are built by Circuit & Chisel, a remote-first team in the US and Canada.

Technical Reference

Release date: September 17, 2026
Context window: 262,144 tokens
Max output tokens: 131,072 tokens
Modalities: Image, Text → Text
Capabilities: streaming, structured output, tool/function calling, vision
Endpoint: POST /v1/chat/completions

What Pareto Brings to the Table

Composite routing without losing the thread
Several models answer the same request and the best response is returned. Because the conversation does not switch models mid-flight, prompt caching survives.

A 262K context window
Long enough for whole repositories, large document sets, or extended agent transcripts, with up to 131,072 tokens back.

Image input
Pareto accepts images alongside text and returns text, so screenshots, diagrams and scanned pages can go straight into the prompt.

Agentic plumbing included
Tool calling, structured (JSON schema) output and streaming are all supported, which is what agent loops need to plan, call tools and iterate.

Where Pareto Makes the Most Sense

Coding and code review
Generate, debug and review code across languages, reading whole files or repositories in a single prompt.

Agentic and multi-step workflows
Reliable tool calling and structured output suit agent loops that plan, call tools and iterate.

Research over long sources
Summarise and extract from papers, contracts and reports without aggressive chunking.

Multimodal analysis
Read charts, screenshots and scanned documents alongside the surrounding text.

Use cases

Code generation, debugging and repository-scale review
Agentic workflows with tool calling and structured output
Research and summarisation over long documents
Multimodal analysis of screenshots, diagrams and scanned pages
General-purpose assistants needing frontier quality at lower cost

Capabilities

Streaming
Structured outputs
Function calling
Vision

Pareto API pricing

Pareto pricing in US dollars
Usage	Price	Unit
Input	$2.65	1M tokens
Output	$7.93	1M tokens
Cached input	$0.2645	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Pareto vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Pareto	$2.65	$7.93
Pareto 26.10	$0.8464	$3.39
Pareto 26.10 Preview	$0.8464	$3.39
Medium 3.5	$1.59	$7.93
Kimi K2.7 Code HighSpeed	$1.9	$8

How to use the Pareto API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "unbiased/pareto",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "unbiased/pareto",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "unbiased/pareto",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Pareto FAQ

What is the context window of Pareto?

Pareto has a 262,144 token context window and can return up to 131,072 tokens.

What inputs and outputs does Pareto support?

Pareto takes image and text as input and returns text. Screenshots, diagrams and scanned pages can go into the prompt alongside the text.

How much does Pareto cost?

Pareto costs $2.65 input and $7.93 output per 1M tokens on AI/ML API, billed as you go with no subscription.

What does it mean that Pareto is a composite model?

Pareto is not a single set of weights. It runs several models against the same request and returns the best answer. Because it does not switch models mid-conversation, prompt caching keeps working across turns.

Does Pareto support tool calling and structured output?

Yes. Pareto supports function calling, structured (JSON schema) output, streaming and vision, the set an agent loop needs to plan, call tools and iterate.

Who created Pareto?

Pareto was built by Unbiased. Unbiased and Pareto are developed and maintained by Circuit & Chisel, a remote-first team across the US and Canada. The model was released on September 17, 2026.

Does Pareto support streaming?

Yes, Pareto can stream responses as they are generated.

How do I call Pareto through AI/ML API?

Pareto is served on the OpenAI-compatible chat completions endpoint. Point any OpenAI SDK at https://api.aimlapi.com/v1 and set the model to unbiased/pareto. The short alias pareto also resolves to it.

What is the Pareto model ID?

Use unbiased/pareto as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Start building with Pareto

Get API key

Pareto API

unbiased/pareto

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "unbiased/pareto",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "unbiased/pareto",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "unbiased/pareto",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Pareto API

Pareto overview

Pareto by Unbiased

Pareto specs

What Is Pareto API?

Technical Reference

What Pareto Brings to the Table

Where Pareto Makes the Most Sense

Use cases

Capabilities

Pareto API pricing

Pareto vs other models: token prices

How to use the Pareto API

Build with your agent

1Get your API key

2Make your first request

Pareto FAQ

Start building with Pareto

Pareto API

Build with your agent

1Get your API key

2Make your first request

Pareto API

Pareto overview

Pareto by Unbiased

Pareto specs

What Is Pareto API?

Technical Reference

What Pareto Brings to the Table

Where Pareto Makes the Most Sense

Use cases

Capabilities

Pareto API pricing

Pareto vs other models: token prices

How to use the Pareto API

Build with your agent

1Get your API key

2Make your first request

Models similar to Pareto

Pareto 26.10

Pareto 26.10 Preview

Qwen3.8 2.4T A95B

Command A

GPT-5.1-Codex-Max

GPT-5 Image Mini

Pareto FAQ

Start building with Pareto