API Cost Check
Claude Haiku 5.5 API pricing
Anthropic model · context 1,000,000 tokens · max output 128,000 · vision, reasoning. Data last changed 2026-10-08. Official pricing ↗ · Data synced from the LiteLLM price list 2026-10-08.
| Input | $0.10 / 1M tokens |
|---|---|
| Output | $0.50 / 1M tokens |
| Cached input | $0.01 / 1M tokens |
| Cache write | $0.125 / 1M tokens |
| Cache write (1-hour TTL) | $0.20 / 1M tokens |
| Batch input | $0.05 / 1M tokens |
| Batch output | $0.25 / 1M tokens |
| Batch cached input | $0.005 / 1M tokens |
| Batch cache write | $0.0625 / 1M tokens |
| Minimum cacheable prompt | 512 tokens |
What it costs per month
| Scenario (per month) | Claude Haiku 5.5 |
|---|---|
| Customer support chatbot 5,000 req/day · 1,200 in · 400 out · cache 60% | $38.51 |
| RAG over documents 2,000 req/day · 8,000 in · 600 out · cache 30% | $53.64 |
| Coding agent 1,500 req/day · 25,000 in · 2,000 out · cache 80% | $79.31 |
| Deep reasoning 800 req/day · 3,000 in · 6,000 out · cache 20% | $77.90 |
| Batch processing 50,000 req/day · 1,500 in · 150 out · batch | $169 |
Adjust the numbers in the calculator.
Cheaper alternatives
Lowest monthly cost for the chatbot scenario among reasoning models:
- Qwen Turbo — $21.00/mo
- MiMo V2.6 Flash — $27.18/mo
- GPT-5 nano — $28.14/mo
- Gemini 2.5 Flash Lite — $32.28/mo
- Qwen Flash — $33.00/mo
Comparisons
Price history
- 2026-10-08: Added — → —