Claude Haiku 4.5 (latest) pricing and specs

Fast Claude lane for lightweight agents, office tasks, and responsive chat

84,51 ₽input / 1M$1
423 ₽output / 1M$5
200Kcontexttokens
64Kmax outputtokens

Claude Haiku 4.5 (latest) price per 1M tokens

Type₽ / 1M$ / 1M
Input tokens84,51 ₽$1
Output tokens423 ₽$5
Cache read8,45 ₽$0.1
Cache write106 ₽$1.25

Prices in rubles as of 18.09.2026 at the CBR rate: 1 $ = 84.51 ₽.

Claude Haiku 4.5 (latest) specs and limits

Context window
200K
Max output
64K
Input
text, image, pdf
Output
text
Family
claude-haiku
Released
2025-10-15
Updated
2025-10-15
Knowledge cutoff
2025-02-28
Also known as
claude ai haiku 4.5 (latest), anthropic haiku 4.5 (latest), claude api haiku 4.5 (latest), claude opus haiku 4.5 (latest), claude sonnet haiku 4.5 (latest)

What Claude Haiku 4.5 (latest) can do

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments / files
  • Vision (images)
  • Temperature control
  • Open weights

Claude Haiku 4.5 (latest) benchmarks

BenchmarkScoreMetric
SWE-Bench Pro39.45resolve rate

Frequently asked questions

How much does the Claude Haiku 4.5 (latest) API cost?

Input costs $1 per 1M tokens (84.51 ₽) and output costs $5 per 1M (423 ₽). Anthropic bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 84.51 ₽ per dollar for September 2026.

How much do 1,000 Claude Haiku 4.5 (latest) tokens cost?

List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $1 for input and $5 for output by 1,000. The same rates in rubles are 84.51 ₽ and 423 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.

How many tokens does Claude Haiku 4.5 (latest) hold?

The Claude Haiku 4.5 (latest) context window is 200K tokens (200,000). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Anthropic model card as of September 2026.

What are the Claude Haiku 4.5 (latest) limits?

The context window is 200K tokens (200,000) and a single response is capped at 64K tokens, so longer output has to be generated in parts. Rate limits are set by Anthropic per account and depend on your plan rather than on the model, so they are not listed here.

How is the Claude Haiku 4.5 (latest) price in rubles calculated?

Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 84.51 ₽ per dollar. For Claude Haiku 4.5 (latest) that gives 84.51 ₽ per 1M input tokens and 423 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.

How is Claude Haiku 4.5 (latest) different from other Claude models?

Claude Haiku 4.5 (latest) belongs to the Claude Haiku family at Anthropic. Models in the Claude line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Claude model is listed on the provider page.

Can Claude Haiku 4.5 (latest) reason?

Yes, Claude Haiku 4.5 (latest) declares a reasoning mode: it works through intermediate steps before it answers. Those steps add output tokens, so a call with a long reasoning chain costs more and takes longer than a plain completion. Capabilities declared for the model: reasoning, tool calling, image input, structured output.

What capabilities does Claude Haiku 4.5 (latest) support?

The declared capabilities of Claude Haiku 4.5 (latest) are: reasoning, tool calling, image input, structured output. It accepts text, images, PDF as input, and every attachment consumes tokens from the shared context window of 200K tokens. The list comes from the Anthropic model card and is refreshed with the catalog as of September 2026.

Other Anthropic models