NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT 6 Astra

Added Sep 3, 2026

Compare models

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

Loading models…

Use in the app

OpenAI's most capable model for the hardest end-to-end work, with state-of-the-art performance in computer use, browsing, software engineering, science, and professional tasks. Astra is designed to carry long, multistep workflows across code, browsers, and professional software through to a finished result.

  • 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
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50

Reference prices as published by the model provider. API example

Specifications

Context window
1.1M
Max output
128K
Average output (7 days)
768 tokens
Longer than 64% of 473 models

Side by side

GPT 6 Astra 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 AstraOpenAIThis modelGPT 6.1 Sol ProOpenAIRemove
ProviderOpenAIOpenAI
Discovery tierFrontierFrontier
AddedSep 3, 2026Sep 29, 2026
Limits
Context window1.05M1.05M
Max output128K128K
Average output768 tokens1.2K tokens
Pricing, USD per 1M tokens
Input$10.00$2.00Best
Output$50.00$10.00Best
Cache read$1.00$0.10Best
Cache write$12.50$2.50Best
Performance
Throughput112.2 tok/s—
Time to first token24.3 s—
Request success (24h)97.2%100.0%Best
Benchmark indexes
Intelligence Index49.6—
Coding Index76.7—
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 Astra
  • GPT 6.1 Sol Pro

Intelligence Index

  • GPT 6 Astra49.6
  • GPT 6.1 Sol Pro—

GPT 6 Astra tested at medium reasoning effort

GPT 6 Astra: Better than 96% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT 6 Astra: 76.7
    • GPT 6.1 Sol Pro: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT 6 Astra: 64.6%
    • GPT 6.1 Sol Pro: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT 6 Astra: 33.6%
    • GPT 6.1 Sol Pro: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT 6 Astra: 1,460 Elo
    • GPT 6.1 Sol Pro: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT 6 Astra: 1,487 Elo
    • GPT 6.1 Sol Pro: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT 6 Astra: 30.4%
    • GPT 6.1 Sol Pro: —

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT 6 Astra: 79.7%
    • GPT 6.1 Sol Pro: —

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT 6 Astra: 38.3%
    • GPT 6.1 Sol Pro: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT 6 Astra: 52.7%
    • GPT 6.1 Sol Pro: —

  • GPQA Diamond

    Graduate-level science questions

    • GPT 6 Astra: 93.9%
    • GPT 6.1 Sol Pro: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT 6 Astra: 49.5%
    • GPT 6.1 Sol Pro: —

  • SciCode

    Scientific computing in Python

    • GPT 6 Astra: 54.2%
    • GPT 6.1 Sol Pro: —

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT 6 Astra: 79.7%
    • GPT 6.1 Sol Pro: —

Scores from Artificial Analysis, updated Oct 26, 2026. GPT 6 Astra 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
112.2 tok/s
Faster than 66% of 256 models
Time to first token
24.3 s
Quicker than 0% of 256 models
Prompt cache hits
68.8%
About $3.81 per 1M input tokens with caching
Request success (24h)
97.2%
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 80.0%
  • 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-astra",
    "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-astra",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.