Text model
anthropic.claude-sonnet-5 pricing
Amazon Bedrock charges $2.40 per million input tokens and $12.00 per million output tokens for anthropic.claude-sonnet-5, and $0.24 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $2.40/ 1M
- Output
- $12.00/ 1M
- Cached input
- $0.24/ 1M
- Context
- 1Mtokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $2.40 | $12.00 | $0.24 | $3.00 |
USD per million tokens. One-hour cache writes cost $4.80. 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 | $0.0084 | 100,000 | $840.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.01 | 100,000 | $1,176.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.02 | 250,000 | $5,280.00 |
| 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-sonnet-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/xai.grok-4.6 | $0.00594 | 29% |
| bedrock/amazon.nova-2-pro-preview-20251202-v1:0 | $0.00588 | 30% |
| anthropic/claude-sonnet-5 | $0.007 | 17% |
| anthropic/claude-sonnet-5-5 | $0.007 | 17% |
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.