Text model
claude-haiku-4-5 pricing
Azure AI Foundry charges $1.00 per million input tokens and $5.00 per million output tokens for claude-haiku-4-5, and $0.10 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $1.00/ 1M
- Output
- $5.00/ 1M
- Cached input
- $0.10/ 1M
- Context
- 200Ktokens
Retires 2026-11-15. npx @veqen/sdk scan finds every place your code uses it.
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $1.00 | $5.00 | $0.10 | $1.25 |
USD per million tokens. One-hour cache writes cost $2.00. 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 | $0.0035 | 100,000 | $350.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0049 | 100,000 | $490.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0088 | 250,000 | $2,200.00 |
| 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 claude-haiku-4-5, 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 |
|---|---|---|
| azure-ai/grok-4.3 | $0.00287 | 18% |
| azure-ai/MAI-Cyber-1-Flash | $0.0023 | 34% |
| openai/gpt-5.4-mini | $0.00293 | 16% |
| databricks/databricks-gpt-5-4-mini | $0.00292 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Azure AI Foundry pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.