Claude Haiku 5.5 API pricing.
Claude Haiku 5.5 by Anthropic costs $0.10 per million input tokens and $0.50 per million output tokens, with a 1M-token context window. That puts it in the budget range of the models we track. A support chatbot handling 10,000 conversations a month would cost about $4.00 a month in API fees.
Price
What Claude Haiku 5.5 costs per token
List prices, checked every hour. Blended assumes three input tokens for every output token. This model sits in the budget range of the models we track.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.20 | 1M |
Source: Claude Haiku 5.5 in the OpenRouter model catalog. Check it against Anthropic's Claude API pricing.
Specs
What Claude Haiku 5.5 can do
From Claude Haiku 5.5's entry in the OpenRouter model catalog.
- Reads
- text, images and files (PDFs and documents)
- Writes
- text
- Context window
- 1M tokens
- Longest answer
- 128K tokens
- Tool calling
- Yes: it can call functions and APIs you define
- Structured output
- Yes: answers can follow a JSON schema
- Reasoning
- Yes: it can think through steps before answering
- Cached input
- $0.01 per 1M tokens (90% off the input price)
- Prompts over 100K tokens
- $0.50 in / $2.50 out per 1M
- Open weights
- No: API access only
Monthly cost
What common workloads cost on Claude Haiku 5.5
API fees only, at list price. The assumptions are shown, so you can scale them to your own volume.
Customer support chatbot
$4.00 / month
10,000 conversations a month, ~1,500 in and ~500 out each: 15M input and 5M output tokens.
Knowledge-base Q&A (RAG)
$12.00 / month
20,000 questions a month, ~4,000 in and ~400 out each: 80M input and 8M output tokens.
Document summaries and extraction
$3.20 / month
2,000 documents a month, ~12,000 in and ~800 out each: 24M input and 1.6M output tokens.
Coding assistant for a team of 10
$6.00 / month
10 developers a month, 3.0M in and 0.6M out each: 30M input and 6M output tokens.
Hosting, a vector database, monitoring and the build itself are extra. The free StackLift estimate adds them for your exact scope.
Per request
What one request costs on Claude Haiku 5.5
A request costs its input tokens times the input price plus its output tokens times the output price. A typical assistant turn of 2,000 input and 500 output tokens on Claude Haiku 5.5: 2,000 × $0.10 ÷ 1M + 500 × $0.50 ÷ 1M = $0.0004.
| Request | Input / output tokens | One request | 1,000 requests |
|---|---|---|---|
| Short chat reply | 500 / 200 | $0.0001 | $0.15 |
| Typical assistant turn | 2,000 / 500 | $0.0004 | $0.45 |
| Long document task | 20,000 / 1,500 | $0.0027 | $2.75 |
As you grow
Claude Haiku 5.5 cost at ten times less and ten times more
The same workloads at a tenth and at ten times the volume, at Claude Haiku 5.5's list price.
| Workload | A tenth | Typical | Ten times |
|---|---|---|---|
| Customer support chatbot | $0.401,000 conversations | $4.0010,000 conversations | $40.00100,000 conversations |
| Knowledge-base Q&A (RAG) | $1.202,000 questions | $12.0020,000 questions | $120200,000 questions |
| Document summaries and extraction | $0.32200 documents | $3.202,000 documents | $32.0020,000 documents |
Fit
When Claude Haiku 5.5 is the right choice
Claude Haiku 5.5 is priced for volume: classification, extraction, routing and short replies, where thousands of requests a day must stay cheap. Hard reasoning may need a larger model for some steps.
Its 1M-token context window fits long contracts, codebases or document sets in one request, though sending that much text on every call raises the bill quickly.
Claude Haiku 5.5 reads images and files (PDFs and documents) as well as text and can call tools and APIs, return structured JSON and reason through multi-step problems, so it can drive agents that act in your systems.
Many products mix models: a cheaper one for simple steps and a stronger one where quality matters. Test a shortlist on your own examples before you commit.
Save
Ways to pay less for Claude Haiku 5.5
1. Cache repeated instructions
Claude Haiku 5.5 charges $0.01 per million cached input tokens instead of $0.10. A 4,000-token system prompt sent with 10,000 requests a month costs $4.00 at the list price and about $0.40 when cached.
2. Route by difficulty
Send simple requests to a cheaper model and keep the stronger one for the steps that need it.
3. Stay under 100K tokens a prompt
Above 100K prompt tokens, Claude Haiku 5.5 charges $0.50 per million input tokens instead of $0.10. Retrieve the passages a question needs rather than sending whole documents.
4. Ask for shorter answers
Output costs 5 times as much as input on Claude Haiku 5.5, so a tight answer format (bullet points, JSON, a word limit) cuts the bill more than a shorter prompt.
Alternatives
Models priced closest to Claude Haiku 5.5
From other providers, nearest on blended price. Quality and speed differ by task: test the shortlist on your own examples.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.20 | 1M |
| Qwen3.8 Omni Flash | Qwen | $0.15 | $0.47 | $0.23 | 1M |
| Qwen3.8 Flash | Qwen | $0.15 | $0.47 | $0.23 | 1M |
| Llama 4 Scout | Meta | $0.10 | $0.30 | $0.15 | 1.3M |
| DeepSeek V3.2 | DeepSeek | $0.26 | $0.38 | $0.29 | 164K |
| Saba | Mistral | $0.20 | $0.60 | $0.30 | 33K |
Anthropic
Other Anthropic models
The same provider's newest models, for a quicker or more capable option.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Claude Fable 5.2 | Anthropic | $8.00 | $40.00 | $16.00 | 1M |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $4.00 | 1M |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | $8.00 | 1M |
Questions about Claude Haiku 5.5 pricing
How much does Claude Haiku 5.5 cost per 1,000 tokens?
$0.0001 per 1,000 input tokens and $0.0005 per 1,000 output tokens, from the list price of $0.10 and $0.50 per million.
Is Claude Haiku 5.5 cheaper than Qwen3.8 Omni Flash?
Yes, on list price. Claude Haiku 5.5 averages $0.20 per million tokens (3 parts input to 1 output) against $0.23 for Qwen3.8 Omni Flash. Quality and speed differ by task, so test both on your own examples.
What is Claude Haiku 5.5's context window?
1M tokens: the most text the model reads and writes in one request. Long documents beyond that are split, or retrieved in parts with RAG.
How much would a chatbot cost on Claude Haiku 5.5?
About $4.00 a month for 10,000 conversations a month, ~1,500 in and ~500 out each. Caching repeated instructions and routing simple questions to a cheaper model lower it further.
Does Claude Haiku 5.5 support tool calling?
Yes. Claude Haiku 5.5 can call functions and APIs you describe to it, which is what lets an AI agent look up data or take actions. It can also return answers that follow a JSON schema.
Can Claude Haiku 5.5 read images or documents?
Yes. Besides text, Claude Haiku 5.5 reads images and files (PDFs and documents).
How long can Claude Haiku 5.5's answers be?
Up to 128K tokens per answer (about 96,000 words), within a 1M tokens context window.
Does Claude Haiku 5.5 have prompt caching?
Yes. Input read from the cache costs $0.01 per million tokens, 90% less than the $0.10 list price, which suits long system prompts and shared context.
How do I estimate the AI cost of my own product?
Count the requests a month and the tokens in and out of each, then multiply by the prices here. StackLift's free estimate does this for your exact scope, alongside the cost to build it.
Build with it
Scope a product on Claude Haiku 5.5
Pick your features and integrations; the estimate returns the build cost, timeline and team, and the model's monthly running cost. Free, no signup.