Claude Haiku pricing: Haiku 5.5 and Haiku 4.5
Claude Haiku is Anthropic's fastest and cheapest model, built for high-volume work such as classification, extraction and routing. This page shows its prices, the long-prompt tier, and what a request costs, with comparisons to Sonnet. Part of our AI costs and pricing section.
Prices last verified against official provider pages on . How we verify prices. Written by the Chelure Enterprises Editorial Team.
Prices per million tokens
| Model | Input | Output | Cached input (read) | Cache write (5 min) | Batch API | Announced change |
|---|---|---|---|---|---|---|
| Claude Haiku 5.5 (prompts up to 100K tokens) | $0.10 | $0.50 | $0.01 | $0.125 | Yes (50% off) | - |
| Claude Haiku 4.5 | $1.00 | $5.00 | $0.10 | $1.25 | Yes (50% off) | - |
Verified November 13, 2026 against the provider's pricing page. Compare every provider in the price comparison, or model your own workload in the cost calculator.
What each model is for
| Model | Positioning (provider) | Context window | Max output |
|---|---|---|---|
| Claude Haiku 5.5 (prompts up to 100K tokens) | For high-volume, latency-sensitive tasks such as classification, extraction and routing; fastest comparative latency | 1M tokens | 128K tokens |
| Claude Haiku 4.5 | Previous Haiku generation | 200K tokens | 64K tokens |
What a request costs
Costs per single request, from the prices above. Agent step uses cache reads at each model's cached-input rate; the 30,000-token step is under Haiku 5.5's 100K tier.
| Model | Chat turn (1,500 input / 400 output tokens, no caching) | RAG answer (8,000 input / 500 output tokens, no caching) | Agent step (30,000 input / 2,000 output tokens, 80% of input read from cache) | 1,000 chat turns |
|---|---|---|---|---|
| Claude Haiku 5.5 (prompts up to 100K tokens) | $0.0003 | $0.0010 | $0.0018 | $0.35 |
| Claude Haiku 4.5 | $0.0035 | $0.011 | $0.018 | $3.50 |
The two-tier price
Haiku 5.5 is listed "from" $0.10 input and $0.50 output per million tokens: those rates apply to prompts up to 100K tokens, and prompts over 100K tokens are billed at $0.50 input and $2.50 output. The table above uses the short-prompt rate, so a long-context Haiku job costs about five times what the table shows. If you routinely send very long prompts, model the higher rate in the cost calculator before assuming Haiku is the cheapest option.
At short-prompt rates Haiku 5.5 is a tenth of Sonnet 5.5's input price per token ($0.10 against $2), which is why Anthropic points it at routing, extraction and other high-volume steps. A common pattern is to use Haiku to classify or pre-filter requests and send only the hard ones to Sonnet or Opus.
Frequently asked questions
How much does Claude Haiku 5.5 cost?
From $0.10 per million input tokens and $0.50 per million output tokens for prompts up to 100K tokens. Prompts over 100K tokens are billed at $0.50 input and $2.50 output per million tokens.
What is Haiku for?
Anthropic positions Haiku 5.5 for high-volume, latency-sensitive tasks such as classification, extraction and routing, and lists it as the fastest of the current models.
Is Haiku 5.5 much cheaper than Haiku 4.5?
Haiku 4.5 lists at $1 input and $5 output per million tokens, ten times the short-prompt price of Haiku 5.5, per Anthropic's models overview.
What is the Haiku context window?
Haiku 5.5 has a 1M-token context window and 128K maximum output; Haiku 4.5 has 200K context and 64K output.
Does the long-prompt price apply to the whole request?
Yes for the request that crosses the threshold. Anthropic says a request whose prompt is over 100,000 tokens pays the higher prices, that the prompt length counts all input tokens including cache reads and writes, and that each request is priced on its own, so earlier requests keep the prices they were billed at.
Sources
Primary sources opened on November 13, 2026. Prices come from our verified price table (see the methodology).