Text model
DeepSeek-V4-Flash-0731 pricing
Azure AI Foundry charges $0.44 per million input tokens and $1.32 per million output tokens for DeepSeek-V4-Flash-0731, and $0.014 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.44/ 1M
- Output
- $1.32/ 1M
- Cached input
- $0.014/ 1M
- Context
- 1Mtokens
Retires 2026-12-03. npx @veqen/sdk scan finds every place your code uses it.
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.44 | $1.32 | $0.014 | — |
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 | $0.00119 | 100,000 | $118.80 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0016 | 100,000 | $159.60 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00293 | 250,000 | $732.00 |
| 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 DeepSeek-V4-Flash-0731, 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-code-fast-1 | $0.0009 | 24% |
| azure-ai/Codestral-2501 | $0.00081 | 32% |
| together/Qwen/Qwen3.7-Plus | $0.000992 | 16% |
| deepinfra/google/gemini-3.1-flash-lite | $0.000975 | 18% |
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.