A rate per million tokens is not a budget. The calculator takes your request volume, prompt size and cache hit rate and gives you a monthly figure.
Claude Haiku 5.5 API pricing (October 2026)
Priced by prompt length: a request whose prompt is over 100K tokens bills entirely at $0.50 in / $2.50 out (cache read $0.05, cache write $0.625).
What it costs at real volumes
A chat-shaped workload: 800 input tokens and 300 output tokens per request, no caching, no batch.
Specifications
- Provider
- Anthropic Claude
- Context window
- 1.0M tokens
- Max output
- 128K tokens
- Tier
- small
- Status
- GA
- Blended $/1M (3:1)
- $0.200
- Cache break-even hit rate
- 22%
- Prices verified
- 12 Oct 2026
Source: Anthropic Claude pricing. Finitizer is not affiliated with Anthropic Claude.
Similar models
Other Claude models
- Claude Fable 5.1+$19.80
- Claude Opus 5.5+$7.80
- Claude Sonnet 5.5+$3.80
- Claude Opus 5+$9.80
- Claude Sonnet 5+$3.80
- Claude Opus 4.1+$29.80
- Claude Sonnet 4.5+$5.80
- Claude Haiku 4.5+$1.80
- Claude Haiku 3.5+$1.40
Closest prices elsewhere
- GPT-6 Lunasame price
- GPT-4.1 nano-$0.025
- Gemini 2.5 Flash-Lite-$0.025
- GPT-4o mini+$0.062
Frequently asked questions
How much does Claude Haiku 5.5 cost per 1M tokens?
Claude Haiku 5.5 costs $0.100 per million input tokens and $0.500 per million output tokens at Anthropic Claude list prices. Output is 5.0x the input rate, so the input:output ratio of your workload drives the real cost more than the headline price.
Does Claude Haiku 5.5 support prompt caching?
Yes. Cached input is billed at $0.010 per million tokens, 10x cheaper than uncached input. Cache writes carry a premium, so caching only pays above roughly a 22% hit rate.
What is the batch discount for Claude Haiku 5.5?
Requests submitted through the asynchronous batch endpoint are billed at 50% off both input and output rates, bringing input to $0.050 and output to $0.250 per million tokens.
What is Claude Haiku 5.5's context window?
1.0M tokens of context with up to 128K output tokens per request. A larger context window raises the ceiling on what you can send, not the price per token, but filling it on every request is one of the most common causes of an unexpected bill.
Running Claude Haiku 5.5 in production?
Finitizer Tokenomics reads what this model actually costs you from your own bills and exports, shows which workload, team or API key is spending it, flags a spike or a new spend source the day your data shows it, and forecasts where the month will land.
See how Finitizer works