NOUMENOpen app
NOUMEN

agnes · Efficient

Agnes 3.0 Flash

Added Sep 9, 2026

Compare models

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

Loading models…

Use in the app

Agnes 3.0 Flash is a low-cost model for coding, tool use, and multi-turn agent tasks. It supports text and image input, optional thinking, and a 512K-token context window.

  • Reasoning
  • Tools
  • Vision
Input
Text, Images
Output
Text
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.05
Output
$0.15
Cache read
$0.005

Reference prices as published by the model provider. API example

Specifications

Context window
524.3K
Max output
65.5K
Average output (7 days)
864 tokens
Longer than 67% of 468 models

Side by side

Agnes 3.0 Flash 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…

Agnes 3.0 FlashagnesThis modelSolar Mini 4upstageRemove
Provideragnesupstage
Discovery tierEfficientEfficient
AddedSep 9, 2026Sep 23, 2026
Limits
Context window524.29K524.29K
Max output65.54K131.07KBest
Average output864 tokens561 tokens
Pricing, USD per 1M tokens
Input$0.05$0.05
Output$0.15Best$0.20
Cache read$0.005$0.005
Performance
Throughput75.9 tok/s90.8 tok/sBest
Time to first token5.2 s2.2 sBest
Request success (24h)90.8%Best89.1%
Benchmark indexes
Intelligence Index—24.1
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesNo
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • Agnes 3.0 Flash
  • Solar Mini 4

Intelligence Index

  • Agnes 3.0 Flash—
  • Solar Mini 424.1
3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 22.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 2.4%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 867 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 1,085 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 5.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 83.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 6.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 25.8%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 1.0%

  • SciCode

    Scientific computing in Python

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 47.6%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Agnes 3.0 Flash: —
    • Solar Mini 4: 83.3%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
75.9 tok/s
Faster than 54% of 259 models
Time to first token
5.2 s
Quicker than 32% of 259 models
Prompt cache hits
92.5%
About $0.0084 per 1M input tokens with caching
Request success (24h)
90.9%
Unstable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 66.6%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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": "agnes-3.0-flash",
    "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="agnes-3.0-flash",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)