Anthropic Claude Haiku 5.5: Pricing, Specs and Limits
Anthropic Claude Haiku 5.5: small, fast model for high-volume work, 1M context, 0.10 in / 0.50 out per 1M tokens. Specs, limits and test prompts.
By ShilpBot Team · Published · 3 min read
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarisation, subagents and browser use. It succeeds Claude Haiku 4.5 with stronger coding and computer use, according to the listing.
At $0.10 per million input tokens and $0.50 per million output tokens it costs one-eightieth as much as Claude Fable 5.2 per output token, and it still has a 1M-token context window.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
Anthropic Claude Haiku 5.5 quick facts
| Detail | Value |
|---|---|
| Developer | Anthropic |
| Model ID | anthropic/claude-haiku-5.5 |
| Added to the catalogue | 2026-10-07 |
| Type | Small, fast model for high-volume work |
| Parameters | Not listed |
| Context window | about 1M tokens (1,000,000) |
| Maximum output | 128,000 tokens |
| Input types | text, image, file |
| Price | 0.10 in / 0.50 out per 1M tokens (cached input 0.010) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What Anthropic Claude Haiku 5.5 is good for
- Summarising large volumes of text at low cost.
- Subagents inside a larger agent system.
- Browser-use and computer-use steps, which the listing highlights.
Limits of Anthropic Claude Haiku 5.5
- It is the small model in the family, so hard reasoning belongs to larger ones.
- Cached input is only $0.01 per million tokens, so design prompts to reuse prefixes.
- Check outputs on tasks that need deep multi-step logic.
How Anthropic Claude Haiku 5.5 compares
- Anthropic Claude Sonnet 5.5: Both have a 1,000,000-token context window; both cap output at 128,000 tokens; it costs 0.10 input and 0.50 output per million tokens against 2.00 and 10.00.
- Anthropic Claude Fable 5.2: Both have a 1,000,000-token context window; both cap output at 128,000 tokens; it costs 0.10 input and 0.50 output per million tokens against 8.00 and 40.00.
- OpenAI GPT-6 Luna: It has a smaller context window (1,000,000 against 1,050,000 tokens); both cap output at 128,000 tokens; it costs 0.10 input and 0.50 output per million tokens against 0.10 and 0.50.
Calling Anthropic Claude Haiku 5.5 from code
Use the model ID anthropic/claude-haiku-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-haiku-5.5", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what Anthropic Claude Haiku 5.5 can do
- Summarise 20 articles in two sentences each and check three against the sources.
- Use it as a subagent that extracts facts for a larger model.
- Compare with Sonnet 5.5 on a bug-fix task to see where it falls short.
What Anthropic Claude Haiku 5.5 costs
The catalogue lists 0.10 per million input tokens and 0.50 per million output tokens, with cached input at 0.010 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.15. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.020 before caching. If your client reuses the same prompt prefix, cached input at 0.010 per million tokens can cut the input side of that bill by about 90 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
What is Claude Haiku 5.5 best used for?
High-volume, cost-sensitive work such as summarisation, subagents and browser use, according to Anthropic's listing.
What are the cost and limits of Anthropic Claude Haiku 5.5?
As of 2026-11-16 the catalogue lists 0.10 per million input tokens and 0.50 per million output tokens. About 1M tokens (1,000,000) context window, up to 128,000 output tokens, model ID anthropic/claude-haiku-5.5. Prices can change, so check the live model page.
