Claude Haiku 5.5 pricing
Anthropic · API id claude-haiku-5-5 · verified 2026-10-18
| Input | $0.10 |
| Cached input (cache hit) | $0.01 |
| Cache write | $0.13 |
| Output | $0.50 |
| Batch discount | 50% |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Above 100K prompt tokens | $0.50 in / $2.50 out |
USD per 1M tokens unless noted. Official source
Estimate your workload on Claude Haiku 5.5 →
What Claude Haiku 5.5 costs for real workloads
| Workload | Claude Haiku 5.5 | Ministral 3 8B | GPT-6 Luna | Mistral Small 4 | Codestral |
|---|---|---|---|---|---|
| 10,000 chatbot replies 2,000 input + 400 output tokens each, 50% of the prompt cached | $3.10 | $2.25 | $3.10 | $4.05 | $6.90 |
| One 30-step coding agent run 12K system + tools prompt, 1K output and 3K tool result per step, caching on | $0.12 | $0.05 | $0.05 | $0.07 | $0.13 |
| 1M documents classified (batch) 600 input + 20 output tokens each, batch API where available | $35.00 | $46.50 | $35.00 | $51.00 | $99.00 |
Compared with the cheapest other small models. Change the numbers in the calculator.
Billing notes
Priced by prompt length: prompts over 100K tokens (incl. cache reads/writes) pay 5x rates for the whole request. Batch: $0.05/$0.25 (<=100K), $0.25/$1.25 (>100K).
Where Claude Haiku 5.5 ranks by use case
Position by cost among all models that fit each workload (1 = cheapest).
- Cheapest LLM for coding agents: #6 of 36 (Per run (cached): $0.12)
- Cheapest LLM for RAG chatbots: #1 of 36 (Per 1,000 answers: $0.67)
- Cheapest LLM for batch classification and extraction: #1 of 36 (Classify 1M docs: $35.00)
- Long-context document analysis (400K tokens): #7 of 29 (10 questions, cached: $0.48)
- Cheapest LLM for high-volume customer support: #2 of 36 (Per 1,000 replies: $0.27)
Counting tokens for a prompt? The token counter estimates Claude Haiku 5.5 tokens (Claude 4.7 and later tokenizer, estimated) and input cost.
Head-to-head comparisons
- Claude Haiku 5.5 vs GPT-6 Luna
- Claude Haiku 5.5 vs Gemini 3.5 Flash-Lite
- Claude Haiku 5.5 vs DeepSeek V4.1 Flash
- Claude Haiku 5.5 vs Mistral Small 4
- Claude Haiku 5.5 vs Claude Haiku 4.5
Other Anthropic models
- Claude Fable 5.1: $10.00 / $50.00
- Claude Opus 5: $5.00 / $25.00
- Claude Opus 4.8: $5.00 / $25.00
- Claude Opus 5.5: $4.00 / $20.00
- Claude Sonnet 4.6: $3.00 / $15.00
- Claude Sonnet 5.5: $2.00 / $10.00
- Claude Sonnet 5: $2.00 / $10.00
- Claude Haiku 4.5: $1.00 / $5.00
FAQ
How much does Claude Haiku 5.5 cost per 1M tokens?
Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens at standard rates (verified 2026-10-18).
Does Claude Haiku 5.5 support prompt caching?
Yes. Cached input is billed at $0.01 per 1M tokens, and writing to the cache costs $0.13 per 1M tokens.
Is there a batch discount for Claude Haiku 5.5?
Yes. The batch API is 50% cheaper than standard requests.
What is the context window of Claude Haiku 5.5?
1,000,000 tokens, with up to 128,000 output tokens. Prompts over 100,000 tokens are billed at $0.50 input and $2.50 output for the whole request.