Anthropic Claude Sonnet 5.5: Pricing, Specs and Limits
Anthropic Claude Sonnet 5.5: Sonnet-class model for well-scoped everyday work, 1M context, 2.00 in / 10.00 out per 1M tokens. Specs, limits and test prompts.
By ShilpBot Team · Published · 3 min read
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work and a direct upgrade to Claude Sonnet 5. The listing says it is especially strong at building features, fixing bugs and producing polished output.
It sits between Haiku 5.5 (cheaper and faster) and Fable 5.2 (most capable and far more expensive), at $2 input and $10 output per million tokens.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Anthropic Claude Sonnet 5.5 quick facts
| Detail | Value |
|---|---|
| Developer | Anthropic |
| Model ID | anthropic/claude-sonnet-5.5 |
| Added to the catalogue | 2026-09-28 |
| Type | Sonnet-class model for well-scoped everyday work |
| Parameters | Not listed |
| Context window | about 1M tokens (1,000,000) |
| Maximum output | 128,000 tokens |
| Input types | text, image, file |
| Price | 2.00 in / 10.00 out per 1M tokens (cached input 0.10) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What Anthropic Claude Sonnet 5.5 is good for
- Feature building and bug fixing on well-defined tasks.
- Writing and document work with a 1M-token window and file input.
- A balanced default when you are not sure which Claude to use.
Limits of Anthropic Claude Sonnet 5.5
- "Well-scoped" matters: vague, open-ended tasks may need a stronger model.
- Cost grows with long agent loops. Use caching.
- For simple summarisation Haiku 5.5 is much cheaper.
How Anthropic Claude Sonnet 5.5 compares
- Anthropic Claude Haiku 5.5: Both have a 1,000,000-token context window; both cap output at 128,000 tokens; it costs 2.00 input and 10.00 output per million tokens against 0.10 and 0.50.
- Anthropic Claude Fable 5.2: Both have a 1,000,000-token context window; both cap output at 128,000 tokens; it costs 2.00 input and 10.00 output per million tokens against 8.00 and 40.00.
- OpenAI GPT-6.1 Sol: It has a smaller context window (1,000,000 against 1,050,000 tokens); both cap output at 128,000 tokens; it costs 2.00 input and 10.00 output per million tokens against 2.00 and 10.00.
Calling Anthropic Claude Sonnet 5.5 from code
Use the model ID anthropic/claude-sonnet-5.5 with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "anthropic/claude-sonnet-5.5", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Anthropic Claude Sonnet 5.5 can do
- Give it a clearly written feature request and a small codebase and ask for the diff.
- Ask it to rewrite a rough memo into a polished one without changing facts.
- Run the same bug on Haiku 5.5 and Sonnet 5.5 and compare.
What Anthropic Claude Sonnet 5.5 costs
The catalogue lists 2.00 per million input tokens and 10.00 per million output tokens, with cached input at 0.10 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 3.00. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.40 before caching. If your client reuses the same prompt prefix, cached input at 0.10 per million tokens can cut the input side of that bill by about 95 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
Which Claude 5.5 model should I choose?
Use Haiku 5.5 for high-volume cheap tasks, Sonnet 5.5 as the balanced default, and Fable 5.2 only for the hardest technical problems.
What are the cost and limits of Anthropic Claude Sonnet 5.5?
As of 2026-11-16 the catalogue lists 2.00 per million input tokens and 10.00 per million output tokens. About 1M tokens (1,000,000) context window, up to 128,000 output tokens, model ID anthropic/claude-sonnet-5.5. Prices can change, so check the live model page.
