Text model
anthropic.claude-haiku-5-5 pricing
Amazon Bedrock charges $0.12 per million input tokens and $0.60 per million output tokens for anthropic.claude-haiku-5-5, and $0.012 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.12/ 1M
- Output
- $0.60/ 1M
- Cached input
- $0.012/ 1M
- Context
- 1Mtokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.12 | $0.60 | $0.012 | $0.15 |
| Standard, prompts over 100K tokens | $0.60 | $3.00 | $0.06 | $0.75 |
USD per million tokens. One-hour cache writes cost $0.24. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00042 | 100,000 | $42.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.000588 | 100,000 | $58.80 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00106 | 250,000 | $264.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with anthropic.claude-haiku-5-5, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| bedrock/openai.gpt-oss-20b-1:0 | $0.00027 | 36% |
| bedrock/amazon.nova-lite-v1:0 | $0.000186 | 56% |
| deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.000355 | 15% |
| nebius/NousResearch/Hermes-4-70B | $0.000355 | 15% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Amazon Bedrock pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.