NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Opus 4.8 Thinking

Added May 28, 2026

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

Anthropic Claude Opus 4.8 with thinking enabled.

  • 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
$5.00
Output
$25.00
Cache read
$0.50

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
128K
Average output (7 days)
1.3K tokens
Longer than 82% of 473 models

Side by side

Compare models

Put Claude Opus 4.8 Thinking next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryGLM 5.3 Flash TEEGPT 5.6 TerraLing 3.1 FlashAll 3

Public evaluations

Benchmarks

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

Intelligence Index

41.8

Tested at max reasoning effort

Better than 86% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    74.3

    Composite of the coding evaluations

    Better than 86% of 168 scored models

Agentic work

  • AutomationBench-AA

    45.6%

    Workflow automation, penalized for guardrail violations

    Better than 60% of 173 scored models

  • AutomationBench-AA tasks completed

    17.4%

    Workflows finished end to end without a guardrail violation

    Better than 63% of 173 scored models

  • AA-Briefcasev1.1

    1,319 Elo

    Agentic knowledge work, rated head to head

    Better than 68% of 166 scored models

  • GDPval-AAv2.1

    1,454 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 73% of 187 scored models

Document reasoning

  • GDP.pdf

    22.8%

    Professional reasoning over PDF documents, all-pass rate

    Better than 81% of 171 scored models

  • AA-LCRv1.1

    77.7%

    Reasoning across long documents

    Better than 64% of 309 scored models

  • MLCR-AA

    19.4%

    Long-context reasoning over medical records

    Better than 80% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    48.7%

    Expert-level questions across academic fields

    Better than 92% of 323 scored models

  • GPQA Diamond

    92.0%

    Graduate-level science questions

    Better than 86% of 291 scored models

  • IFBench

    62.2%

    Following precise output instructions

    Better than 61% of 215 scored models

Coding

  • Terminal-Benchv4.0

    21.7%

    Practical software engineering in a terminal

    Better than 74% of 171 scored models

  • SciCode

    54.4%

    Scientific computing in Python

    Better than 72% of 174 scored models

Legacy evaluations

  • Terminal-Bench Hard

    58.3%

    Earlier terminal task suite

    Better than 97% of 212 scored models

  • τ²-Bench Telecom

    94.4%

    Tool use in a customer-support simulation

    Better than 85% of 214 scored models

  • AA-LCR (unversioned)

    77.7%

    Long-context reasoning, earlier grading

    Better than 64% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Opus 4.8 Thinking was tested at max 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
168.5 tok/s
Faster than 80% of 260 models
Time to first token
5.7 s
Quicker than 26% of 260 models
Prompt cache hits
75.6%
About $1.60 per 1M input tokens with caching
Request success (24h)
100.0%
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 100.0%
  • 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": "anthropic/claude-opus-4.8:thinking",
    "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="anthropic/claude-opus-4.8:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.