Claude Haiku 5.5
Pricing & Specs
Anthropic · $0.1 input / $0.5 output per 1M tokens · 1M context window
The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on Claude Haiku 5.5 costs about $0.0003, roughly $0.35 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.
Claude Haiku 5.5 API Pricing
| Tokens | Price |
|---|---|
| Input | $0.1 / 1M tokens |
| Output | $0.5 / 1M tokens |
| Cached input | $0.01 / 1M tokens |
Priced by prompt length: prompts over 100,000 tokens (all input incl. cache reads/writes) are billed at the higher tier for the whole request. Cache writes: $0.125/MTok (5min), $0.20/MTok (1hr) up to 100K; $0.625/$1 over 100K. 50% batch discount. Min cacheable prompt 512 tokens.
What that means in practice
Claude Haiku 5.5 Specs
| Spec | Value |
|---|---|
| Context window | 1M tokens |
| Max output tokens | 128K tokens |
| Input modalities | text, image |
| Output modalities | text |
| Knowledge cutoff | Jun 2026 |
| Reasoning model | Yes |
| Tool / function calling | Yes |
| JSON mode | Yes |
| Streaming | Yes |
| Prompt caching | Yes |
| Batch API | Yes |
Notes
Released October 7, 2026. For high-volume, latency-sensitive tasks (classification, extraction, routing, subagents). Adaptive thinking on by default, default effort medium. Omit temperature/top_p/top_k (non-default returns 400). Newer tokenizer: ~30% more tokens than Haiku 4.5. Thinking blocks only usable in the producing account.
FAQ
How much does Claude Haiku 5.5 cost?
Claude Haiku 5.5 costs $0.1 per 1M input tokens and $0.5 per 1M output tokens ($0.01 per 1M cached input tokens).
What is Claude Haiku 5.5's context window?
Claude Haiku 5.5 has a 1M-token context window. Maximum output is 128K tokens.
Can I test Claude Haiku 5.5 on my own task?
Yes. OpenMark lets you benchmark Claude Haiku 5.5 against 100+ models on your own task with real API calls, with no API keys needed, free tier available.
Is Claude Haiku 5.5 the right model for YOUR task?
Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload: real API calls, real costs. Free tier available.