Claude Sonnet 5.5
Claude Sonnet 5.5 is a large language model made by Anthropic, added to the catalog on 28 Sep 2026. It has a context window of 1,000,000 tokens and costs $2.00 per 1M input tokens and $10.00 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: building software features, fixing software bugs and working with image and file inputs.
Price checked · source: OpenRouter
What Claude Sonnet 5.5 is
Claude Sonnet 5.5 is Anthropic’s Sonnet-class model for well-scoped everyday work. Its catalog description highlights building features and fixing bugs, and identifies it as a direct upgrade to Claude Sonnet 5. It accepts text, images and files, and produces text. Listed capabilities include reasoning, tools, structured outputs and response formats. These support applications that provide tools or request outputs in a specified format, although the catalog does not name particular tools or formats. The model is listed for coding work as well as everyday tasks.
Claude Sonnet 5.5 has a context window of 1,000,000 tokens and a maximum output of 128,000 tokens. The context limit gives it room to receive large amounts of material in a single interaction, while the output limit allows for long text responses when needed. Its input modalities make it suitable for tasks that combine written instructions with image or file content. The catalog does not specify supported file formats, image limits or how these inputs are handled. The stated coding focus makes feature-building and bug-fixing assistance relevant uses. Reasoning and tool support are also listed capabilities for applications that include those functions in a task. The facts do not provide performance measures or further detail about the model’s behavior, so its suitability for a particular workflow depends on that workflow’s requirements.
Key features
- Accepts text, image and file inputs
- Produces text
- Supports a context window of 1,000,000 tokens
- Maximum output is 128,000 tokens
- Supports tools, structured outputs, response formats and reasoning
Typical uses
- Building software features
- Fixing software bugs
- Working with image and file inputs
- Generating structured text outputs
- Reasoning over supplied information
Claude Sonnet 5.5 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $2.00 | $1.00 |
| Output, per 1M tokens | $10.00 | $5.00 |
| Cached input read, per 1M tokens | $0.10 | $0.05 |
| Cache write, per 1M tokens | $2.50 | $1.25 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | anthropic/claude-sonnet-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 28 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0040 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.058 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.080 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.315 |
Claude Sonnet 5.5 specifications
| Model id | anthropic/claude-sonnet-5.5 |
|---|---|
| Version | claude-sonnet-5.5-20260928 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 28 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 Sonnet 5.5 yet.
Compare Claude Sonnet 5.5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.