Claude Haiku 4.5

Q: What is the API model name for Claude Haiku 4.5?

Use claude-haiku-4-5 in API calls to Anthropic. The context window is 200K tokens, and a response can run to 64,000 output tokens.

Claude Haiku 4.5 API pricing is $1 per million input tokens and $5 per million output tokens.

Provider: Anthropic
API model name: claude-haiku-4-5
Status: Current
Input, $ per 1M tokens: $1.00
Cached input, $ per 1M tokens: $0.10
Output, $ per 1M tokens: $5.00
Sample request (10K in, 2K out), $: $0.02
Context window, tokens: 200K
Price checked on: October 31, 2026
Official pricing page: platform.claude.com

These are standard rates on Anthropic’s own API. It is the cheapest current Claude model. Cached input is billed at $0.10 per million tokens. A request with 10,000 input tokens and 2,000 output tokens costs about $0.02 before caching or batch discounts. The API model name is claude-haiku-4-5, and the context window is 200K tokens, smaller than the 1M of current Opus and Sonnet models. Cache writes cost $1.25 per 1M tokens for a 5-minute cache and $2 for a 1-hour cache.

Cache writes, $ per 1M tokens: $1.25
Max output, tokens: 64K
Input types: Text, image, file
Open weights: No
Batch pricing: 50% off input and output tokens
Pricing notes: Cache writes cost $1.25 per 1M tokens for a 5-minute cache and $2 for a 1-hour cache.
Sources: Page URL Checked
Claude API pricing https://platform.claude.com/docs/en/about-claude/pricing 2026-10-19
OpenRouter model listing (context and output limits) https://openrouter.ai/models 2026-09-29

Page	URL	Checked
Claude API pricing	https://platform.claude.com/docs/en/about-claude/pricing	2026-10-19
OpenRouter model listing (context and output limits)	https://openrouter.ai/models	2026-09-29

Questions

How much does the Claude Haiku 4.5 API cost?

Claude Haiku 4.5 costs $1 per million input tokens and $5 per million output tokens on Anthropic’s own API. Cached input costs $0.10 per million tokens.

What is the API model name for Claude Haiku 4.5?

Use claude-haiku-4-5 in API calls to Anthropic. The context window is 200K tokens, and a response can run to 64,000 output tokens.

What does one Claude Haiku 4.5 request cost?

A request with 10,000 input tokens and 2,000 output tokens costs about $0.02 at standard rates, before caching or batch discounts. Batch requests get 50% off input and output tokens.

How much do Claude Haiku 4.5 cache writes cost?

Cache writes cost $1.25 per 1M tokens for a 5-minute cache and $2 for a 1-hour cache.

Sources

Prices are read from each provider’s official pricing page: OpenAI, Anthropic, Google Gemini API, xAI, DeepSeek and Mistral AI. Context and output limits that a provider does not publish come from OpenRouter’s model listing. Each model’s Sources field lists the pages used and the date each was checked. How we check prices · Price change log