Claude Haiku 5.5: Pricing, Context, and Benchmarks
Claude Haiku 5.5 is Anthropic's Claude 5 model released on 2026-10-07. It runs on a 1.0M-token context window, priced at $0.10/M input and $0.50/M output. Anthropic model for high-volume, latency-sensitive work. Prices shown are for prompts up to 100,000 tokens; prompts over 100,000 tokens cost $0.50 / $2.50 per million.
Specifications
| Provider | Anthropic |
|---|---|
| Family | Claude 5 |
| Released | 2026-10-07 |
| Status | active |
| Context window | 1.0M tokens |
| Max output | 128K tokens |
| Modalities | text image |
| Capabilities | function calling json mode vision streaming tool use thinking |
| Tokenizer | claude (since Opus 4.7) |
| API endpoint | https://api.anthropic.com/v1/messages |
| Documentation | Official docs ↗ |
| Last updated | 2026-11-14 |
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0006 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.000070 | $0.07 | $70 |
| Standard chat | 1K / 500 | $0.000350 | $0.35 | $350 |
| RAG with retrieval | 4K / 500 | $0.000650 | $0.65 | $650 |
| Long doc summary | 20K / 1K | $0.002500 | $2.50 | $2,500 |
| Long context (100K input) | 100K / 2K | $0.010750 | $10.75 | $10,750 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other Anthropic models
- Claude Fable 5.2
- Claude Sonnet 5.5
- Claude Opus 5.5
- Claude Opus 4.7
- Claude Sonnet 4.6
- Claude Haiku 4.5
Common comparisons
- Claude Haiku 5.5 vs GPT-4o Mini Side-by-side specs, pricing, and benchmarks
- Claude Haiku 5.5 vs GPT-5 Nano Side-by-side specs, pricing, and benchmarks
- Claude Haiku 5.5 vs Codestral Side-by-side specs, pricing, and benchmarks
- Claude Haiku 5.5 vs GPT-5 Mini Side-by-side specs, pricing, and benchmarks
API setup
curl https://api.anthropic.com/v1/messages \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-haiku-5-5", "messages": [{"role": "user", "content": "Hello"}]}'See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.