Claude Sonnet 5
Claude Sonnet 5 is a large language model made by Anthropic, added to the catalog on 30 Jun 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: coding tasks, agent workflows and professional work.
Price checked · source: OpenRouter
What Claude Sonnet 5 is
Anthropic: Claude Sonnet 5 is a text-generating model that accepts text, images, and files and produces text. Its catalog entry lists a context window of 1,000,000 tokens and a maximum output of 128,000 tokens. That gives it room to work with extensive supplied context and return long text responses, while the task still depends on the prompt and material provided.
The model supports reasoning, with adaptive thinking and selectable reasoning effort levels of low, medium, high, and max. It also supports tools, structured outputs, and response formats. These options suit workflows that need a response in a specified structure or involve tool-enabled steps; the catalog does not specify particular tools or formats, so those depend on the surrounding application. Anthropic describes the model as intended for coding, agent workflows, and professional work.
The long context is relevant to tasks involving substantial reference material, such as working with extended text or supplied files. Text, images, and files can be included as inputs, while the model’s listed output is text. Its maximum output length allows for extended generated responses. The combination of coding, reasoning, tool support, and structured output can fit varied professional workflows, though the catalog does not specify particular coding languages, tools, or output schemas.
Key features
- Accepts text, image, and file inputs and produces text
- Has a context window of 1,000,000 tokens
- Supports reasoning with low, medium, high, and max effort levels
- Supports tools, structured outputs, and response formats
- Has a maximum output of 128,000 tokens
Typical uses
- Coding tasks
- Agent workflows
- Professional work
- Working with extensive reference material
- Generating structured text responses
Claude Sonnet 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 | $0.20 | $0.10 |
| 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: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 30 Jun 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 specifications
| Model id | anthropic/claude-sonnet-5 |
|---|---|
| Version | claude-sonnet-5-20260630 |
| Context window | 1,000,000 tokensAbout 750,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 30 Jun 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 yet.
Compare Claude Sonnet 5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.