NOUMENOpen app
NOUMEN

fetchai · Efficient

ASI1 Mini

Added Mar 25, 2025

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

ASI-1 Mini introduces next-level adaptive reasoning, context-aware decision-making. It features native reasoning support with four dynamic reasoning modes, intelligently selecting from Multi-Step, Complete, Optimized, and Short Reasoning, balancing depth, efficiency, and precision. Whether tackling complex, multi-layered problems or delivering concise, high-impact insights, ASI-1 Mini ensures reasoning is always tailored to the task at hand. Note: this model is rate limited at the moment.

  • PDF input
Input
Text
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$1.00
Output
$1.00

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
16.4K

Side by side

ASI1 Mini compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

ASI1 MinifetchaiThis modelOpenAI o3-mini (Low)OpenAIRemove
ProviderfetchaiOpenAI
Discovery tierEfficientEfficient
AddedMar 25, 2025Jan 31, 2026
Limits
Context window128K200KBest
Max output16.38K100KBest
Pricing, USD per 1M tokens
Input$1.00Best$1.10
Output$1.00Best$4.40
Cache read—$0.55
Benchmark indexes
Intelligence Index—12.5
Capabilities
ReasoningNoYes
ToolsNoYes
Structured outputNoYes
PDF inputYesNo
Reasoning effort—low, medium, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • ASI1 Mini
  • OpenAI o3-mini (Low)

Intelligence Index

  • ASI1 Mini—
  • OpenAI o3-mini (Low)12.5
3.8Catalog models by score55.1

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 7.9%

  • GPQA Diamond

    Graduate-level science questions

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 74.8%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 79.1%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 71.7%

Math

  • AIME

    Competition mathematics

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 77.0%

  • MATH-500

    Competition math problems

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 97.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 6.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • ASI1 Mini: —
    • OpenAI o3-mini (Low): 28.7%

Scores from Artificial Analysis, updated Oct 26, 2026.

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "asi1-mini",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="asi1-mini",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)