Claude Opus 5.5
Claude Opus 5.5 is a large language model made by Anthropic, added to the catalog on 22 Sep 2026. It has a context window of 1,000,000 tokens and costs $4.00 per 1M input tokens and $20.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: multi-step changes in large codebases, long-horizon, tool-assisted workflows and reasoning over text, images, and files.
Price checked ยท source: OpenRouter
What Claude Opus 5.5 is
Claude Opus 5.5 is Anthropic's model for demanding reasoning, coding, and long-horizon agentic work. The provider describes it as particularly suited to multi-step changes in large codebases. It accepts text, images, and files, and produces text. Its listed capabilities include reasoning and tool support, as well as structured outputs and response-format controls.
With a context length of 1,000,000 tokens, it can take in a large amount of material in one context, which suits work involving extensive source code, lengthy documents, or multiple related inputs. It can produce up to 128,000 output tokens, allowing for long text responses when a task calls for them. The context figure describes the input window, while the output limit sets the maximum length of a generated response. The facts list no audio input or output; its stated output modality is text.
The combination of code-focused description, reasoning support, and tools makes it relevant to tasks involving changes across a codebase or longer, tool-assisted workflows. Image and file inputs let requests include non-text materials alongside text. Structured outputs and response-format support may be useful when an application needs responses in a defined format. The model is positioned for complex coding and reasoning tasks rather than a narrowly specified single-purpose function.
Key features
- Accepts text, image, and file inputs
- Produces text, with a maximum output of 128,000 tokens
- Has a context length of 1,000,000 tokens
- Supports reasoning and tools
- Supports structured outputs and response formats
Typical uses
- Multi-step changes in large codebases
- Long-horizon, tool-assisted workflows
- Reasoning over text, images, and files
- Generating structured text outputs
Claude Opus 5.5 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $4.00 | $2.00 |
| Output, per 1M tokens | $20.00 | $10.00 |
| Cached input read, per 1M tokens | $0.20 | $0.10 |
| Cache write, per 1M tokens | $5.00 | $2.50 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | anthropic/claude-opus-5.5:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 22 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0080 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.116 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.160 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.630 |
Claude Opus 5.5 specifications
| Model id | anthropic/claude-opus-5.5 |
|---|---|
| Version | claude-opus-5.5-20260921 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 22 Sep 2026 |
| Input types | text, image, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Claude Opus 5.5 yet.
Compare Claude Opus 5.5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.