Standard Compute
← All models
Claude Haiku 5.5 · Anthropic

What does Claude Haiku 5.5 cost to run in a coding agent?

Claude Haiku 5.5 costs about $0.013 per average coding-agent request on our measured traffic, at list prices of $0.10 per million input and $0.50 per million output tokens. It is built for subagents and quick steps; Anthropic reports 39.2% on Terminal-Bench 4.0.

List prices: Anthropic pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. Benchmark: Anthropic announcement. How we compute this

Run Claude Haiku 5.5 in your agent from $19/month

See plans

What Haiku 5.5 costs per coding-agent request

Cost at list priceHaiku 5.5
Prompt under 100K tokens50% of requests, 87% of input cached$0.0016
Prompt of 100K to 272K39% of requests, 88% of input cached$0.020
Prompt over 272K tokens11% of requests, 86% of input cached$0.043
Average request$0.013
100 requests$1.31
Median session16 requests; a session ends after 10 idle minutes$0.096
A month of regular usemedian of 20 users active on 5+ days$17.73

Each logged request priced at the vendor's list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

What to watch for

50% of the coding-agent requests in our data were over 100K tokens, where every token costs five times more. Under 100K a request costs $0.0016, the same as on GPT-6 Luna. Between 100K and 272K it costs $0.020, against $0.0039 on Luna.

Where Haiku 5.5 sits on the Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index bar chart with Claude Haiku 5.5 (max) highlighted, from artificialanalysis.ai, October 13, 2026
Artificial Analysis Intelligence Index v4.3.2, Claude Haiku 5.5 (max) highlighted, downloaded October 13, 2026. Source: Artificial Analysis (artificialanalysis.ai)

About Claude Haiku 5.5

Claude Haiku 5.5 is Anthropic's fast, low-cost model, released October 7, 2026 and pitched for classification, extraction, routing and coding subagents under Opus 5.5 or Sonnet 5.5. It is the first Haiku with adjustable effort and a 1M-token context window. Artificial Analysis scores it 43 on its Intelligence Index (max effort) at about 236 output tokens per second, and Anthropic reports 39.2% on Terminal-Bench 4.0 where Haiku 4.5 scored 0%. Pricing has two bands: prompts over 100K tokens are billed at five times the base rate on every token, which matters for coding agents whose context grows during a session.

Sources: Anthropic announcement · Artificial Analysis · SWE-Bench Pro V2

Agents that run Haiku 5.5 well

Subagents, routing and high-volume steps that stay under 100K tokens per request.

Not sure which Claude to run? Best Claude model in 2026: Opus vs Sonnet vs Haiku →

Claude Haiku 5.5 FAQ

How much does Claude Haiku 5.5 cost per coding-agent request?
$0.013 on average at list price, $1.31 per 100 requests, and $0.096 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at Anthropic's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.
Does Claude Haiku 5.5 charge more for long prompts?
Yes. Prompts over 100K tokens are billed at $0.50 per million input and $2.50 per million output tokens, on every token in the request including cache reads. 50% of the coding-agent requests we measured were that large.
Is Claude Haiku 5.5 good for AI agents?
Subagents, routing and high-volume steps that stay under 100K tokens per request. On our editorial scoring it rates 9.0/10 for agentic ability and 9.1/10 for output quality. Far stronger than Haiku 4.5 (Artificial Analysis 43 vs 17).
What is Claude Haiku 5.5's context window?
Claude Haiku 5.5 has a 1M-token context window — large enough to hold sizeable codebases or document sets in a single run. Anthropic is the maker.
Can I self-host Claude Haiku 5.5?
No — Claude Haiku 5.5 is a proprietary, hosted-only model from Anthropic. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.
What are the downsides of Claude Haiku 5.5?
The main trade-offs: Prompts over 100K tokens cost 5x, on the whole request; New tokenizer counts about 30% more tokens than Haiku 4.5 for the same text. It's strongest for subagents, routing and high-volume steps that stay under 100K tokens per request.

Haiku 5.5 compared

The agent matters as much as the model. Which agent gets the most out of Haiku 5.5? →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Opus 5.5 · Claude Sonnet 5.5

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. The most intelligence per dollar. One flat bill.

Plans from $19/mo · cancel anytime · 7-day fair refund

7-day fair refund No credit card needed Billing by Stripe1,800+ agent users