Post-Cutoff
Search For AI agents

AnthropicClaude 4 familyLegacyReasoning modelReleased 5 Feb 2026

Claude Opus 4.6

Legacy Opus; migrate to claude-opus-5-5.

Model idclaude-opus-4-6

Price$5 in, $25 out per 1M tokens

Checked29 September 2026

Knows up to May 2025

2,019events after its cutoff

89 historic, 467 major. 531 days of news.

It launched on 5 February 2026, already missing 77 of them. Coverage before 2026 is thin (80 entries for 2025), so this count is a floor.

Five things it has never heard of

Its cutoff, May 2025, is before this chart starts: every mark here is news it has never seen.

How to call it

7 ways to use Claude Opus 4.6, with the model id each provider expects.

Providers, model ids, endpoints and docs for Claude Opus 4.6
ProviderModel idEndpointDocs
Anthropic API (Claude API) claude-opus-4-6 https://api.anthropic.com/v1/messages platform.claude.com
AWS Bedrock (InvokeModel) anthropic.claude-opus-4-6-v1 platform.claude.com
Google Cloud Vertex AI claude-opus-4-6 platform.claude.com
Microsoft Foundry (Azure) claude-opus-4-6 platform.claude.com
Claude Platform on AWS claude-opus-4-6 platform.claude.com
OpenRouter anthropic/claude-opus-4.6 openrouter.ai
Web app claude.ai

Pricing

Prices for Claude Opus 4.6
Input$5 per 1M tokens
Output$25 per 1M tokens
Cache read$0.50 per 1M tokens

As published: “per 1M tokens (USD); Batch API 50% off”.

Source: platform.claude.com, checked 29 September 2026.

Specs

Input
Text, images and PDF
Output
Text
Context window
1,000,000 tokens
Max output
128,000 tokens
Open weights
No
Licence
Proprietary
Training cutoff
May 2025
Released
5 February 2026
Status
Legacy
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • 1M-token context for Opus

    First

    First Opus with a 1M-token context window (launched in beta). Scored 76% on MRCR v2 long-context retrieval versus 18.5% for Sonnet 4.5.

    Source: anthropic.com

  • Adaptive thinking

    First

    Introduced adaptive thinking: the model decides when and how much to think, steered by effort.

    Source: anthropic.com

  • Agent teams

    First

    Research preview of multiple Claude instances coordinating in parallel (in Claude Code).

    Source: anthropic.com

  • Knowledge work (GDPval-AA)

    About 144 Elo above GPT-5.2 on GDPval-AA. Also led Terminal-Bench 2.0 at launch.

    Source: anthropic.com

Four assistants, one scale

Claude Opus 4.6 is added as a fifth row. Each row runs from what the model knows (graphite) through the months between its cutoff and its launch (hatched) to today (pink).

  1. GPT-6 Astra 271 at launch, 1,863 today
  2. Claude Opus 5.5 372 at launch, 1,795 today
  3. Gemini 4 Hydrogen 1,863 at launch, 1,889 today
  4. Grok 4.7 387 at launch, 1,829 today
  5. Claude Opus 4.6 77 at launch, 2,019 today
Show as a table
ModelCutoffReleasedMissing at launchMissing today
GPT-6 AstraApril 20263 September 20262711,863
Claude Opus 5.5June 202622 September 20263721,795
Gemini 4 HydrogenMarch 202612 November 20261,8631,889
Grok 4.7May 202621 September 20263871,829
Claude Opus 4.6May 20255 February 2026772,019

Notes

First dateless-ID Opus; adaptive thinking (budget_tokens deprecated). Training data cutoff Aug 2025. Bedrock via InvokeModel only. Retirement not sooner than 2027-02-05.

curl https://api.anthropic.com/v1/messages \
 -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" -H "content-type: application/json" \
 -d '{"model":"claude-opus-4-6","max_tokens":16000,"messages":[{"role":"user","content":"Hello"}]}'

Sources: