NOUMENOpen app
NOUMEN

Anthropic · Frontier

Claude 4.6 Opus

Added Feb 5, 2026

Compare models

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

Loading models…

Use in the app

Claude Opus 4.6 supports advanced coding, agentic workflows, and long-context analysis with up to 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)
1.4K tokens
Longer than 84% of 465 models

Side by side

Claude 4.6 Opus 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 4.6 OpusAnthropicThis modelGemini 3 Flash ThinkingGoogleRemove
ProviderAnthropicGoogle
Discovery tierFrontierEfficient
AddedFeb 5, 2026Dec 17, 2025
Limits
Context window1M1.05MBest
Max output128KBest65.54K
Average output1.4K tokens1.7K tokens
Pricing, USD per 1M tokens
Input$5.00$0.50Best
Output$25.00$3.00Best
Cache read$0.50$0.05Best
Performance
Throughput45.8 tok/s—
Time to first token2.1 s—
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index26.4Best26.3
Math Index—97.0
Capabilities
ReasoningYesYes
ToolsYesNo
VisionYesYes
Structured outputYesNo
PDF inputYesNo
Audio inputNoYes
Video inputNoYes
Reasoning effortlow, medium, high, xhigh, maxminimal, low, medium, high

Public evaluations

Benchmarks

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

  • Claude 4.6 Opus
  • Gemini 3 Flash Thinking

Intelligence Index

  • Claude 4.6 Opus26.4
  • Gemini 3 Flash Thinking26.3

Claude 4.6 Opus tested at high reasoning effort

Claude 4.6 Opus: Better than 66% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • Claude 4.6 Opus: —
    • Gemini 3 Flash Thinking: 97.0

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • Claude 4.6 Opus: 67.0%
    • Gemini 3 Flash Thinking: 78.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Claude 4.6 Opus: 19.1%
    • Gemini 3 Flash Thinking: 36.6%Top

  • GPQA Diamond

    Graduate-level science questions

    • Claude 4.6 Opus: 84.0%
    • Gemini 3 Flash Thinking: 89.8%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Claude 4.6 Opus: —
    • Gemini 3 Flash Thinking: 89.0%

  • IFBench

    Following precise output instructions

    • Claude 4.6 Opus: 44.6%
    • Gemini 3 Flash Thinking: 78.0%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Claude 4.6 Opus: —
    • Gemini 3 Flash Thinking: 90.8%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Claude 4.6 Opus: —
    • Gemini 3 Flash Thinking: 97.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Claude 4.6 Opus: 48.5%Top
    • Gemini 3 Flash Thinking: 38.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Claude 4.6 Opus: 84.8%Top
    • Gemini 3 Flash Thinking: 80.4%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Claude 4.6 Opus: 67.0%
    • Gemini 3 Flash Thinking: 78.0%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Claude 4.6 Opus was tested at high 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
45.8 tok/s
Faster than 33% of 250 models
Time to first token
2.1 s
Quicker than 72% of 250 models
Prompt cache hits
2.0%
About $4.91 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 95.8%
  • 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-4.6",
    "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-4.6",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Anthropic

Other Anthropic models, starting with the same family.