Text model
Llama-4-Maverick-17B-128E-Instruct-FP8 pricing
Azure AI Foundry charges $0.25 per million input tokens and $1.00 per million output tokens for Llama-4-Maverick-17B-128E-Instruct-FP8. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.25/ 1M
- Output
- $1.00/ 1M
- Context
- 1Mtokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.25 | $1.00 | — | — |
USD per million tokens. 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 | $0.000775 | 100,000 | $77.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.002 | 100,000 | $200.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0038 | 250,000 | $950.00 |
| 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 Llama-4-Maverick-17B-128E-Instruct-FP8, 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/Llama-4-Scout-17B-16E-Instruct | $0.000612 | 21% |
| azure-ai/FW-GLM-5.3-Flash | $0.000532 | 31% |
| deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct | $0.000652 | 16% |
| deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.00062 | 20% |
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.