NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT 6.1 Sol

Added Sep 29, 2026

Compare models

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

Loading models…

Use in the app

GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It supports text and image input, tool calling, structured outputs, and reasoning from low through max.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$2.00
Output
$10.00
Cache read
$0.10
Cache write
$2.50

Reference prices as published by the model provider. API example

Specifications

Context window
1.1M
Max output
128K
Average output (7 days)
388 tokens
Longer than 39% of 473 models

Side by side

GPT 6.1 Sol 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…

GPT 6.1 SolOpenAIThis modelClaude Opus 5AnthropicRemove
ProviderOpenAIAnthropic
Discovery tierFrontierFrontier
AddedSep 29, 2026Jul 24, 2026
Limits
Context window1.05MBest1M
Max output128K128K
Average output388 tokens1.5K tokens
Pricing, USD per 1M tokens
Input$2.00Best$5.00
Output$10.00Best$25.00
Cache read$0.10Best$0.50
Cache write$2.50Best$6.25
Performance
Throughput147.9 tok/sBest116.0 tok/s
Time to first token5.3 s4.4 sBest
Request success (24h)99.9%99.9%
Benchmark indexes
Intelligence Index47.848.1Best
Coding Index—76.5
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortlow, medium, high, xhigh, maxlow, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • GPT 6.1 Sol
  • Claude Opus 5

Intelligence Index

  • GPT 6.1 Sol47.8
  • Claude Opus 548.1

GPT 6.1 Sol tested at medium reasoning effort

GPT 6.1 Sol: Better than 95% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 6.1 Sol: —
    • Claude Opus 5: 76.5

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 6.1 Sol: 62.6%Top
    • Claude Opus 5: 53.6%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 6.1 Sol: 30.1%Top
    • Claude Opus 5: 25.3%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 6.1 Sol: 1,359 Elo
    • Claude Opus 5: 1,558 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 6.1 Sol: 1,450 Elo
    • Claude Opus 5: 1,595 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 6.1 Sol: 30.0%Top
    • Claude Opus 5: 19.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 6.1 Sol: 83.3%Top
    • Claude Opus 5: 79.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 6.1 Sol: 32.2%Top
    • Claude Opus 5: 11.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 6.1 Sol: 49.9%
    • Claude Opus 5: 52.8%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT 6.1 Sol: —
    • Claude Opus 5: 93.7%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 6.1 Sol: 48.0%Top
    • Claude Opus 5: 46.0%

  • SciCode

    Scientific computing in Python

    • GPT 6.1 Sol: 53.2%
    • Claude Opus 5: 55.4%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 6.1 Sol: 83.3%Top
    • Claude Opus 5: 79.0%

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 6.1 Sol was tested at medium reasoning effort; compare scores measured at the same effort.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
147.9 tok/s
Faster than 76% of 260 models
Time to first token
5.3 s
Quicker than 28% of 260 models
Prompt cache hits
94.8%
About $0.20 per 1M input tokens with caching
Request success (24h)
99.9%
Reliable

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 83.7%
  • 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": "openai/gpt-6.1-sol",
    "reasoning_effort": "medium",
    "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="openai/gpt-6.1-sol",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.