Anthropic · Model
Claude Haiku 5.5 pricing, context window and specs
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens, and reads up to 1,000,000 tokens per request. By blended price it is the cheapest in Anthropic's current line-up.
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Cached / 1M
- $0.01
- Context
- 1,000,000
- Max output
- 128,000
- Released
- 2026-10-07
Estimate your cost with Claude Haiku 5.5Compare all Anthropic modelsCount tokens for Claude Haiku 5.5
Pricing
Claude Haiku 5.5 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.10 | $0.50 |
| Cached input (read) | $0.01 | – |
| Batch API | $0.05 | $0.25 |
| Prompts of 100,000+ tokens | $0.50 | $2.50 |
Output costs 5.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 10% of the normal input price. Once a single prompt reaches 100,000 tokens, the whole request is billed at the higher long-context rate shown above.
Examples
What Claude Haiku 5.5 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.000283 | $8.59 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.000742 | $11.28 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.00212 | $12.90 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.00055 | $5.02 |
Change any number in the cost calculator.
Context
Context window
Claude Haiku 5.5 accepts up to 1,000,000 tokens per request, roughly 750,000 English words or 1,500 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 128,000 tokens.
Filling the whole window with one prompt costs about $0.50 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- text, image, file
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
Anthropic
Where Claude Haiku 5.5 sits in Anthropic’s line-up
Ranked by blended price (three parts input to one part output, $0.20 per 1M for Claude Haiku 5.5), it is the cheapest of Anthropic’s 16 priced models. See every Anthropic model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Claude Haiku 5.5 (this page) | $0.10 | $0.50 | 1,000,000 | 2026-10-07 |
| Claude Sonnet 5.5 | $2 | $10 | 1,000,000 | 2026-09-28 |
| Claude Opus 5.5 | $4 | $20 | 1,000,000 | 2026-09-22 |
| Claude Fable 5.1 | $10 | $50 | 1,000,000 | 2026-09-01 |
| Claude Opus 5 | $5 | $25 | 1,000,000 | 2026-07-24 |
| Claude Sonnet 5 | $2 | $10 | 1,000,000 | 2026-06-30 |
| Claude Fable 5 | $10 | $50 | 1,000,000 | 2026-06-09 |
| Claude Opus 4.8 | $5 | $25 | 1,000,000 | 2026-05-27 |
Save
Cheaper alternatives
- Qwen3.7 FlashQwen73% cheaper
- Seed 1.6 FlashByteDance Seed34% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- Ministral 3 14B 2512Mistral$0.20 / $0.20
- GPT-6 LunaOpenAI$0.10 / $0.50
- Qwen3 VL 8B InstructQwen$0.117 / $0.455
- Seed-2.0-MiniByteDance Seed$0.10 / $0.40
- Nemotron 3 SuperNVIDIA$0.08 / $0.45
Current models from other major providers, closest blended price.
FAQ
Claude Haiku 5.5 questions
How much does Claude Haiku 5.5 cost?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens, with cached input at $0.01. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00035. Use the LLM cost calculator for your own workload.
What is Claude Haiku 5.5's context window?
1,000,000 tokens, about 750,000 English words or 1,500 printed pages, shared between your prompt and the reply. A single reply can be up to 128,000 tokens.
Does Claude Haiku 5.5 support prompt caching and batch requests?
Yes, cached input is billed at $0.01 per million tokens (10% of the normal input price). A batch API is available at $0.05 input and $0.25 output per million tokens.
What are cheaper alternatives to Claude Haiku 5.5?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.7 Flash (73% cheaper), Seed 1.6 Flash (34% cheaper). Cheaper doesn't mean equivalent, so test them on your own prompts.
Is Claude Haiku 5.5 open source?
No, Claude Haiku 5.5 is only available through Anthropic's API and partners; its weights aren't published.