How much does the Claude Haiku 5.5 API cost?

On FastMetal, Claude Haiku 5.5 is billed per token: $0.1055 per 1M input tokens and $0.5275 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Claude Haiku 5.5 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-haiku-5-5" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Claude Haiku 5.5?

1,000,000 tokens, shared between the prompt and the response.

What do I need to try Claude Haiku 5.5?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

Anthropic

anthropic-claude-haiku-5-5

Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

10/7/2026

1,000,000 tokens

Input: $0.1055/M

Output: $0.5275/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

file

Output

text

Supported Parameters

include_reasoning

max_completion_tokens

max_tokens

reasoning

reasoning_effort

response_format

stop

structured_outputs

tool_choice

tools

verbosity

Max Output Tokens

128,000

Reasoning Configuration

Default: Thinking on (effort: medium)
Selectable effort levels: max
xhigh
high
medium
low
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "anthropic-claude-haiku-5-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Claude Haiku 5.5 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

There are **3** r's in "strawberry." 1. **Spell out the word:** s, t, r, a, w, b, e, r, r, y 2. **Go through each letter and count the r's:** - Position 3: **r** (count = 1) - Position 8: **r** (count = 2) - Position 9: **r** (count = 3) 3. **Check the rest:** s, t, a, w, b, e, and y are not r's. Total: **3**

2.4s response200 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

The error means `users` is `undefined` when `UserList` renders, so `.map` is called on nothing. The component destructures the `users` prop, but the parent didn't pass it, or passed `undefined`. ## Common causes **1. The parent doesn't pass the prop, or uses a different name** ```jsx <UserList /> // users is undefined <UserList user={users} /> // wrong name: "user" instead of "users" ``` **2. The data hasn't loaded yet (most common with fetched data)** ```jsx function App() { const [users, setUsers] = useState(); // undefined initially useEffect(() => { fetch('/api/users').then(r => r.json()).then(setUsers); }, []); return <UserList users={users} />;…

5.1s response888 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

## Issues **Correctness and robustness** 1. **Bare `except:`** catches everything, including `KeyboardInterrupt` and `SystemExit`, so Ctrl+C may not stop the program. Catch specific exceptions: `requests.RequestException` for network problems and `ValueError` for invalid JSON. 2. **Retries non-retryable errors.** A 404 or 401 won't succeed on retry, so retrying wastes time. Only retry transient failures such as 429, 5xx, timeouts, and connection errors. 3. **Sleeps after the final attempt.** The loop sleeps even when no retry follows. 4. **Fixed sleep with no backoff.** Exponential backoff is the standard approach for retries. 5. **Silent failure.** Every failure returns `[]` with no loggin…

18.1s response4096 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Claude Haiku 5.5 API cost?: On FastMetal, Claude Haiku 5.5 is billed per token: $0.1055 per 1M input tokens and $0.5275 per 1M output tokens on a US-dollar account, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Claude Haiku 5.5 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "anthropic-claude-haiku-5-5" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Claude Haiku 5.5?: 1,000,000 tokens, shared between the prompt and the response.
What do I need to try Claude Haiku 5.5?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.