Retired Jun 2026
Claude Opus 4
Introduced hybrid reasoning with both instant and extended thinking modes, and built for sustained agentic coding workflows.
Key Specifications
- Context window
- 200K tokens
- Max output
- 32K tokens
- Knowledge cutoff
- Released
- Inputs
- Text, image
- Capabilities Show details
- Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON.
Frequently Asked Questions
What is Claude Opus 4 good for?
Long agentic coding sessions. It introduced the choice of instant or extended thinking, and takes text and images.
When is Claude Opus 4 not a good fit?
Any new work: Anthropic retired it in June 2026, and Opus 4.5 and later replace it. Closed weights, so no self-hosting, and its maximum output is shorter than the later Opus models'.
How does Claude Opus 4 compare with Claude Opus 4.5?
Anthropic says Claude Opus 4.5 improves on Claude Opus 4 in coding, handles ambiguity and tradeoffs with less hand-holding, and stays on track on long tasks while using far fewer tokens. It adds an effort setting to trade speed against depth. Same 200K-token context and text and image input. Claude Opus 4 came out 6 months earlier and has an older knowledge cutoff (March 2025 against May 2025) and a smaller max output (32K against 64K tokens).
Can I self-host Claude Opus 4?
No. Anthropic does not publish the weights; Claude Opus 4 is available only through hosted APIs.
More from Anthropic
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
Claude Fable 5.1
|
1M | $10.00 | $50.00 |
|
Claude Opus 5
|
1M | $5.00 | $25.00 |
|
Claude Fable 5
|
1M | $10.00 | $50.00 |
|
Claude Opus 4.7
|
1M | $5.00 | $25.00 |
|
Claude Opus 4.8
|
1M | $5.00 | $25.00 |
|
Claude Sonnet 5
|
1M | $2.00 | $10.00 |
|
Claude Sonnet 4.6
|
1M | $3.00 | $15.00 |
|
Claude Opus 4.6
|
1M | $5.00 | $25.00 |