Claude Haiku 4.5 (2025-10-01) Thinking API

Input / 1M tokens$0.88~~$1.00~~

Output / 1M tokens$4.40~~$5.00~~

LLMAnthropic12% below officialReasoningAnthropic API

Loading playground…

About Claude Haiku 4.5 (2025-10-01) Thinking

Claude Haiku 4.5 (2025-10-01) Thinking by Anthropic is available on API Many from $0.88 per million input tokens and $4.40 per million output tokens, and you call it with the same API key you use for every other model.

It accepts OpenAI-style chat requests with streaming and tools.

Claude models also speak the Anthropic Messages API at /v1/messages, so the official Anthropic SDK works by changing only the base URL.

You pay only for successful results: failed or rejected requests are refunded automatically, and every call is recorded in your console with its exact cost.

Related models

New−12%

Claude Haiku 5.5claude-haiku-5-5

LLMAnthropic1M contextPrompt caching

$0.088 in · $0.44 outTry it

−12%

Claude Haiku 4.5 (2025-10-01)claude-haiku-4-5-20251001

LLMAnthropic128K contextPrompt caching

$0.88 in · $4.40 outTry it

New−12%

Claude Opus 5.5claude-opus-5-5

LLMAnthropic128K contextPrompt caching

$3.52 in · $17.60 outTry it

New−12%

Claude Sonnet 5.5claude-sonnet-5-5

LLMAnthropic1M contextPrompt caching

$1.76 in · $8.80 outTry it

−12%

Claude Fable 5claude-fable-5

LLMAnthropic1M contextPrompt caching

$8.80 in · $44.00 outTry it

−12%

Claude Fable 5.1claude-fable-5.1

LLMAnthropic1M contextPrompt caching

$8.80 in · $44.00 outTry it

−12%

Claude Opus 4.5 (2025-11-01)claude-opus-4-5-20251101

LLMAnthropicAnthropic API

$4.40 in · $22.00 outTry it

−12%

Claude Opus 4.5 (2025-11-01) Thinkingclaude-opus-4-5-20251101-thinking

LLMAnthropicReasoningAnthropic API

$4.40 in · $22.00 outTry it

Frequently asked questions

How much does the Claude Haiku 4.5 (2025-10-01) Thinking API cost?

Claude Haiku 4.5 (2025-10-01) Thinking starts at $0.88 per million input tokens and $4.40 per million output tokens on API Many. The price table on this page lists every tier; you are charged only for successful requests.

How do I call Claude Haiku 4.5 (2025-10-01) Thinking?

Create an API key in the console, then send a request to /v1/chat/completions with "model": "claude-haiku-4-5-20251001-thinking". The API tab has copy-ready examples in cURL, Python and Node.js.

Is this the official Claude Haiku 4.5 (2025-10-01) Thinking model?

Yes. Requests are forwarded to the model maker or an authorized channel with the same parameters, so the output matches the official API.

What happens if a request fails?

Failed, rejected or timed-out requests are not charged. Reserved balance is released automatically and the reason is shown in the call record.