Verified November 2026

Home › Models › Claude Haiku 5.5

Claude Haiku 5.5 API pricing

Claude Haiku 5.5 is a model from Anthropic with a 200,000-token context window. Rates below are per 1,000,000 tokens, verified November 2026.

$0.10Input / 1M tokens
$0.50Output / 1M tokens
$0.01Cached input / 1M
200,000Context window

Price list

Claude Haiku 5.5 rates in USD per 1M tokens, November 2026
Token classRate / 1MNotes
Input$0.10Prompt tokens not served from cache
Cached input$0.0190% below base input
Cache write$0.125Charged once when the prefix is stored
Output$0.505.0× the input rate
Long context input$0.50Above 100,000 input tokens
Long context output$2.50Same threshold
Batch API−50%Input and output, results within 24 h

Prompts above 100K tokens bill at 5x the short-prompt rate ($0.50/$2.50). The only Claude model with a published input-length step-up.

What Claude Haiku 5.5 costs at three real workloads

Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.

WorkloadRequestsTokensEstimated cost
Support chat1,0004K in / 600 out$0.70
RAG with caching1,00050K in (45K cached) / 1K out$1.46
Nightly batch job10,00010K in / 2K out$10

Caching the 45K-token prefix saves about 74% on the RAG workload versus sending it uncached every call ($5.50 → $1.46). Batch mode halves the nightly job.

Where Claude Haiku 5.5 sits in the market

Out of 45 models in this dataset, Claude Haiku 5.5 ranks #3 cheapest by input rate, #3 by output rate, and #3 on a blended 1M-input-plus-250K-output workload.

ModelProviderInputOutputBlended
Claude Haiku 5.5Anthropic$0.10$0.50$0.225
GPT-6 LunaOpenAI$0.10$0.50$0.225
Qwen 3 32BAlibaba (Qwen)$0.15$0.60$0.30
Qwen 3 8BAlibaba (Qwen)$0.05$0.20$0.10

Blended cost = 1M input tokens + 250K output tokens at list price.

FAQ

How much does Claude Haiku 5.5 cost per 1M tokens?

$0.10 per 1M input tokens and $0.50 per 1M output tokens on the standard tier, rising to $0.50 / $2.50 above 100,000 input tokens.

Is prompt caching cheaper on Claude Haiku 5.5?

Yes. Cached input bills at $0.01 per 1M tokens, 90.0% below the $0.10 base input rate, with a one-off cache write at $0.125 per 1M.

Does Claude Haiku 5.5 support the Batch API?

Yes. Batch requests bill at roughly half the standard input and output rates: the nightly job above costs $20 at list price and about $10 in batch mode.

Keep reading

Run these numbers in the calculator