Claude Opus 5.5
Anthropic's recommended default model. Thinking always on (cannot be disabled); effort default is medium (set explicitly); forced tool_choice any/tool returns 400; computer use only via computer_toolset_20260801 on Claude API/Google Cloud. Fast mode (Claude API only) $8/$40. Batch $2/$10; up to 300K output on Batch with output-300k-2026-03-24 beta.
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Knowledge cutoff
- 2026-06
- Input
- text, image, pdf
- Output
- text
- License
- proprietary
- Pricing
- input: $4 · output: $20 · cache read: $0.2 (per 1M tokens (USD); Batch API 50% off) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Anthropic API (Claude API) | claude-opus-5-5 | https://api.anthropic.com/v1/messages | docs |
| AWS Bedrock (Messages API / Mantle) | anthropic.claude-opus-5-5 | — | docs |
| Google Cloud Vertex AI | claude-opus-5-5 | — | docs |
| Microsoft Foundry (Azure) | claude-opus-5-5 | — | docs |
| Claude Platform on AWS | claude-opus-5-5 | — | docs |
| OpenRouter | anthropic/claude-opus-5.5 | openrouter.ai/anthropic/claude-opus-5.5 | — |
| Web app | — | claude.ai | — |
Notable capabilities (5)
- Top agentic coding at lower cost: Anthropic reports 66.4% on Terminal-Bench 4.0, ahead of GPT-6 Astra at roughly 40% of the cost; an early tester finished a 680k-line code migration in under a day. source
- Knowledge-work lead (GDPval-AA): Launch claim of 1846 Elo on GDPval-AA v2.1, above both Claude Fable 5.1 (1735) and Claude Opus 5 (1708). source
- Cheaper, faster Opus: About 40% cheaper than Opus 5 on typical workloads ($4/$20 per MTok, cache reads $0.20) and about 30% faster output at default settings. source
- FIRST Opus with Fable-level safeguards: Anthropic says it is the first Opus model whose safeguards match Claude Fable 5.1 on cyber, bio and distillation (refusal categories include bio and reasoning_extraction). source
- Thinking that cannot be disabled: Adaptive thinking is always on and effort is the only control (default medium). Text between tool calls comes back as progress-update thinking blocks. source
Default choice for most workloads: long-running agentic coding and knowledge work, cheaper than Claude Opus 5 ($5/$25). Text+image in, text out.
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-5-5","max_tokens":16000,"messages":[{"role":"user","content":"Hello"}]}'
Sources:
- Model page: https://platform.claude.com/docs/en/models/opus-5-5/overview
- Announcement: https://www.anthropic.com/claude-opus-5-5
- Pricing: https://platform.claude.com/docs/en/about-claude/pricing
- Models overview: https://platform.claude.com/docs/en/about-claude/models/overview
- Deprecations: https://platform.claude.com/docs/en/about-claude/model-deprecations
Other Anthropic models
Claude Sonnet 5.5 · Claude Fable 5.1 · Claude Mythos 5.1 · Claude Haiku 4.5 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5 · Claude Opus 4.8 · Claude Opus 4.7 · Claude Sonnet 4.6 · Claude Opus 4.6 · Claude Opus 4.5 · Claude Sonnet 4.5 · Claude Opus 4.1 · Claude Sonnet 4