NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude Opus 4.8

Added May 28, 2026

Compare models

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

Loading models…

Use in the app

Anthropic Claude Opus 4.8 with text, image, and file inputs and a 1M-token context window.

  • 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)
360 tokens
Longer than 37% of 473 models

Side by side

Claude Opus 4.8 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…

Claude Opus 4.8AnthropicThis modelClaude 4.7 Opus ThinkingAnthropicRemove
ProviderAnthropicAnthropic
Discovery tierFrontierFrontier
AddedMay 28, 2026Apr 16, 2026
Limits
Context window1M1M
Max output128K128K
Average output360 tokens1.9K tokens
Pricing, USD per 1M tokens
Input$5.00$5.00
Output$25.00$25.00
Cache read$0.50$0.50
Performance
Throughput81.9 tok/s98.9 tok/sBest
Time to first token1.2 sBest3.0 s
Request success (24h)100.0%Best99.1%
Benchmark indexes
Intelligence Index41.8Best40.7
Coding Index74.3Best73.6
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.

  • Claude Opus 4.8
  • Claude 4.7 Opus Thinking

Intelligence Index

  • Claude Opus 4.841.8
  • Claude 4.7 Opus Thinking40.7

Claude Opus 4.8 tested at max reasoning effort

Claude Opus 4.8: Better than 86% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Claude Opus 4.8: 74.3Top
    • Claude 4.7 Opus Thinking: 73.6

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Claude Opus 4.8: 45.6%
    • Claude 4.7 Opus Thinking: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Claude Opus 4.8: 17.4%
    • Claude 4.7 Opus Thinking: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Claude Opus 4.8: 1,319 EloTop
    • Claude 4.7 Opus Thinking: 1,252 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Claude Opus 4.8: 1,454 EloTop
    • Claude 4.7 Opus Thinking: 1,353 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Claude Opus 4.8: 22.8%
    • Claude 4.7 Opus Thinking: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude Opus 4.8: 77.7%
    • Claude 4.7 Opus Thinking: 78.7%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • Claude Opus 4.8: 19.4%
    • Claude 4.7 Opus Thinking: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude Opus 4.8: 48.7%Top
    • Claude 4.7 Opus Thinking: 42.3%

  • GPQA Diamond

    Graduate-level science questions

    • Claude Opus 4.8: 92.0%Top
    • Claude 4.7 Opus Thinking: 91.4%

  • IFBench

    Following precise output instructions

    • Claude Opus 4.8: 62.2%Top
    • Claude 4.7 Opus Thinking: 58.6%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Claude Opus 4.8: 21.7%
    • Claude 4.7 Opus Thinking: —

  • SciCode

    Scientific computing in Python

    • Claude Opus 4.8: 54.4%
    • Claude 4.7 Opus Thinking: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Claude Opus 4.8: 58.3%Top
    • Claude 4.7 Opus Thinking: 51.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Claude Opus 4.8: 94.4%Top
    • Claude 4.7 Opus Thinking: 88.6%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude Opus 4.8: 77.7%
    • Claude 4.7 Opus Thinking: 78.7%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Claude Opus 4.8 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
81.9 tok/s
Faster than 54% of 256 models
Time to first token
1.2 s
Quicker than 93% of 256 models
Prompt cache hits
28.1%
About $3.74 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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.