Skip to content
AI Atlas
ModelActiveClosed / proprietaryIdentity probable

Claude Opus 4.6

Anthropicfamily · Claude

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Open in Graph
data quality67

Updated 5 h ago · first seen 11 Sept 2026

model_01M293VBD4A1NFA069HJ80AZ8V

Overview

Identity

Canonical model
Yesidentity confidence: mediumOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
None recorded — closed weightsofficial_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
2
API aliases
anthropic/claude-opus-4.6claude-opus-4-6claude-opus-4-6-adaptiveIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
2Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Closed / proprietary— weights not available; 7 dimensions unknown.

Weights are not available; the model is reachable only through an API or a product.

  • Weights

    No

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    —

  • Redistribution

    —

  • Derivatives

    —

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Status

Source:Claude Developer Platform docsT1observed 15 h agohigh

Retirement date

Source:Claude Developer Platform docsT1observed 15 h agohigh

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Architecture

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Capabilities

Modalities

Modalities
documentimagetext
Input
documentimagetext
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Yes

    OpenRouter public model & pricing listing · T2

  • Vision

    Yes

    OpenRouter public model & pricing listing · T2

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 15 h agomedium

Benchmarks38

Compare with another model →

Comparable same task and conditions · Partially comparable same task, conditions differ (effort, temperature, judge) · Not comparable different variant or metric

Benchmark results grouped by comparability group
Benchmark · groupBest scoreTrustConfigurationResultsvs leaderEvaluatedSource
Terminal-Benchagentic · accuracy · variant=hard · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisvarianthardreasoningoffreasoning_efforthighconditions differ across rows → partially comparable4−17.4 ptvs gpt-5.6-solobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · variant=Telecom · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantTelecomreasoningadaptivereasoning_effortmaxconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
τ²-benchagentic · pass^1 · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningadaptiveconditions differ across rows → partially comparable2−7.01 ptvs Z.ai GLM 5.2obs. 11 Sept 2026artificialanalysis.aiT2
LiveBench Agentic Codingcoding · average score · variant=Agentic CodingOfficial boardvariantAgentic Codingreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−28.3 ptvs DeepSeek-V4.1-Flash25 Jun 2026livebench.aiT2
LiveBench Codingcoding · average score · variant=CodingOfficial boardvariantCodingreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−8.19 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
SWE-bench Multilingualcoding · resolved · board=Multilingual · system=mini-SWE-agentOfficial boardboardMultilingualsystemmini-SWE-agent1−0.70 ptvs gemini-3-flash13 Feb 2026swebench.comT2
SWE-bench Verifiedcoding · resolved · board=Verified · system=mini-SWE-agentOfficial boardboardVerifiedsystemmini-SWE-agent1−1.20 ptvs Claude Opus 4.517 Feb 2026swebench.comT2
Artificial Analysis Intelligence Indexcomposite · indexIndependentreasoningadaptivereasoning_effortmaxversion4.3conditions differ across rows → partially comparable4−21.4vs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBenchgeneral · global_averageOfficial boardreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−8.89 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
LiveBench Data Analysisgeneral · average score · variant=Data AnalysisOfficial boardvariantData Analysisreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−13.1 ptvs gpt-6-astra25 Jun 2026livebench.aiT2
LiveBench Languagegeneral · average score · variant=LanguageOfficial boardvariantLanguagereasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−7.41 ptvs Claude Fable 525 Jun 2026livebench.aiT2
IFBenchinstruction-following · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningadaptivereasoning_effortmaxconditions differ across rows → partially comparable4−30.2 ptvs Grok 4.3obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Instruction Followinginstruction-following · average score · variant=IFOfficial boardvariantIFreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−18.1 ptvs Gemini 3.8 Flash25 Jun 2026livebench.aiT2
Humanity's Last Examknowledge · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningadaptivereasoning_effortmaxconditions differ across rows → partially comparable4−19.2 ptvs Claude Fable 5.1obs. 12 Sept 2026artificialanalysis.aiT2
LiveBench Mathematicsmath · average score · variant=MathematicsOfficial boardvariantMathematicsreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−7.69 ptvs Claude Fable 5.125 Jun 2026livebench.aiT2
MMMU-Promultimodal · accuracy · evaluator=Artificial AnalysisIndependentevaluatorArtificial Analysisreasoningadaptivereasoning_effortmaxconditions differ across rows → partially comparable4−11.4 ptvs gpt-6-astraobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantDiamondreasoningadaptivereasoning_effortmaxconditions differ across rows → partially comparable2non-primary groupobs. 12 Sept 2026artificialanalysis.aiT2
GPQA Diamondreasoning · accuracy · variant=GPQA Diamond · evaluator=Artificial AnalysisIndependentevaluatorArtificial AnalysisvariantGPQA Diamondreasoningadaptiveconditions differ across rows → partially comparable2−6.66 ptvs gpt-6-astraobs. 11 Sept 2026artificialanalysis.aiT2
LiveBench Reasoningreasoning · average score · variant=ReasoningOfficial boardvariantReasoningreasoningonreasoning_efforthighrelease2026-06-25conditions differ across rows → partially comparable1−3.98 ptvs gpt-6-astra25 Jun 2026livebench.aiT2

Current rows only, grouped by benchmark → canonical metric → comparability group (task configuration). Effort variants folded into this model appear as rows of the same group. 38 current rows in total. “vs leader” compares with the current leader of the benchmark's primary group only; other groups are not directly comparable. Comparability rules →

Providers & Pricing5

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MCached inCache writeOutput / 1MNative unitsStatusObservedSource
Anthropic APIcheapest outputanthropic/claude-opus-4.6:batch1Mout 128K$0.25$3.13—active6 h agosince 11 Sept 2026openrouter.aiT2
OpenRouteranthropic/claude-opus-4.6:batch1Mout 128K$0.25$3.13—active2 h agosince 12 Sept 2026openrouter.aiT2
Anthropic API—$0.50$6.25cache_write_1h_per_mtok=10active15 h agosince 11 Sept 2026platform.claude.comT1
Anthropic APIanthropic/claude-opus-4.61Mout 128K$0.50$6.25—active6 h agosince 11 Sept 2026openrouter.aiT2
OpenRouteranthropic/claude-opus-4.61Mout 128K$0.50$6.25—active2 h agosince 12 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 2 providers

Output price history of Claude Opus 4.6$0$10$20$30Sept 26Sept 26Sept 26Sept 26Sept 26Anthropic API: first observed → $25 · 11 Sept 2026Anthropic API: $25 → $12.5 · 11 Sept 2026OpenRouter: first observed → $25 · 12 Sept 2026OpenRouter: $25 → $12.5 · 12 Sept 2026
  • Anthropic API
  • OpenRouter
  • OpenRouter$25 → $12.512 Sept 2026
  • OpenRouterfirst observed $2512 Sept 2026
  • Anthropic API$25 → $12.511 Sept 2026
  • Anthropic APIfirst observed $2511 Sept 2026

Input price · USD / 1M tokens 2 providers

Input price history of Claude Opus 4.6$0$2$4$6Sept 26Sept 26Sept 26Sept 26Sept 26Anthropic API: first observed → $5 · 11 Sept 2026Anthropic API: $5 → $2.5 · 11 Sept 2026OpenRouter: first observed → $5 · 12 Sept 2026OpenRouter: $5 → $2.5 · 12 Sept 2026
  • Anthropic API
  • OpenRouter
  • OpenRouter$5 → $2.512 Sept 2026
  • OpenRouterfirst observed $512 Sept 2026
  • Anthropic API$5 → $2.511 Sept 2026
  • Anthropic APIfirst observed $511 Sept 2026

Versions & Artifacts0

Version history

Status1 change

11 Sept 2026→11 Sept 2026current

Context windowfirst observation only

11 Sept 2026current

Max outputfirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Timeline19

Full timeline →

Change history

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.
1 claims · 1 propertiesShow all properties

Aa opennessaa_openness1

Claim history for Aa openness
ValueValid from → toStatusSourceConfidenceExtractor
proprietary → currentcurrentArtificial AnalysisT2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

26

Source tiers

T1T25 / 21

Freshest observation

5 h ago

Conflicts

1 flagged

Source documents 6

Source documents
SourceDocumentTypeTierLast observedSnapshots
Claude Developer Platform docsdocs.claude.com/en/docs/about-claude/model-deprecations.md model_docsT1· Official3 h ago1
Claude Developer Platform docsdocs.claude.com/en/docs/about-claude/pricing.md pricingT1· Official3 h ago1
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary2 h ago11
SWE-bench leaderboardsswebench.com/ leaderboardT2· Quality secondary5 h ago1
Artificial Analysisartificialanalysis.ai/leaderboards/models leaderboardT2· Quality secondary5 h ago2
LiveBenchlivebench.ai/table_2026_06_25.csv leaderboardT2· Quality secondary13 h ago1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (67/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →