Anthropic
Claude Haiku 5.5 pricing and benchmarks
Anthropic’s fastest, lowest-cost model, priced by prompt length, with a 1M-token context window.
Input
$0.10
per 1M tokens
Cached input
$0.01
per 1M tokens
Output
$0.50
per 1M tokens
Capability index
159.0
#11 of 25 tracked
How capable is Claude Haiku 5.5?
Claude Haiku 5.5 scores 159.0 on the Epoch Capabilities Index (confidence interval 156.6–162.1), ranking #11 of the 25 rated models we track. It is a best-value pick: no cheaper model we track scores higher.
| Benchmark | Tests | Score |
|---|---|---|
| GPQA Diamond | Science reasoning | 89.6% |
| FrontierMath (Tiers 1–3) | Advanced math | 75.1% |
| SimpleQA Verified | Factual accuracy | 23.8% |
| ARC-AGI-2 | Abstract reasoning | — |
| DeepSWE | Coding | — |
| APEX-Agents | Agentic work | 56.1% |
Source: Epoch AI (as “Claude Haiku 5.5”), best recorded result, CC BY 4.0. A dash means no published score. Compare all models
What Claude Haiku 5.5 costs in practice
| Workload | Monthly cost |
|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $35.00 |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $55.00 |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $24.80 |
Pricing details
- Prompts over 100K tokens, counting cache reads and writes, are billed at $0.50 input / $2.50 output per 1M tokens.
- Cache writes cost $0.125 (5-minute cache) or $0.20 (1-hour cache) per 1M tokens, 5x that above 100K tokens.
- US-only inference (inference_geo: "us") costs 1.1x.
Estimate your Claude Haiku 5.5 bill
- Claude Haiku 5.5Anthropic$55.00/mo$0.0011 / request
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.