DeepSeek V4 Flash 0731 API Pricing
DeepSeek · Budget · Apache 2.0 · released 2026-07. Prices in USD per 1 million tokens. Data snapshot: 2026-09-11.
- Input: $0.07 per 1M tokens
- Output: $0.18 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.02
- Context window: 1M
- Available on: Direct API, OpenRouter (curated by hand, verify with the provider)
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.000188 | $0.000143 | $14 |
| Knowledge Q&A | 2,000 / 800 | $0.000274 | $0.000205 | $21 |
| Meeting Summary | 10,000 / 1,200 | $0.000866 | $0.000817 | $82 |
| Marketing Content | 2,500 / 1,800 | $0.000486 | $0.000462 | $46 |
| Coding Task | 3,000 / 2,000 | $0.000555 | $0.000481 | $48 |
| Invoice Processing | 1,500 / 600 | $0.000206 | $0.000183 | $18 |
| Call Summary | 2,000 / 700 | $0.000256 | $0.000246 | $25 |
| Agent Workflow | 6,000 / 3,000 | $0.000930 | $0.000724 | $72 |
DeepSeek V4 Flash 0731 pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 27 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-11 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| OpenInference — fp8 | $0.05 | $0.16 |
| DeepInfra — fp8 | $0.06 | $0.18 |
| Relace (the price shown above) — fp4 | $0.07 | $0.18 |
| StreamLake — fp8 | $0.06 | $0.18 |
| Makora | $0.09 | $0.20 |
| Inceptron — fp4 | $0.09 | $0.25 |
| DigitalOcean | $0.08 | $0.25 |
| Wafer | $0.10 | $0.25 |
| BaseTen — fp8 | $0.13 | $0.26 |
| Sail Research — fp4 | $0.07 | $0.30 |
| CoreWeave — fp8 | $0.13 | $0.28 |
| Together | $0.14 | $0.28 |
| Parasail — fp8 | $0.14 | $0.28 |
| Morph — bf16 | $0.12 | $0.35 |
| Venice | $0.17 | $0.35 |
| Mancer 2 — fp8 | $0.17 | $0.50 |
| Alibaba | $0.18 | $0.53 |
| Reka — fp4 | $0.11 | $0.66 |
| Fireworks | $0.22 | $0.66 |
| SiliconFlow — fp8 | $0.22 | $0.66 |
| GMICloud — fp4 | $0.29 | $0.86 |
| NextBit — fp8 | $0.35 | $1.06 |
| Novita — fp8 | $0.41 | $1.23 |
| Phala | $0.44 | $1.32 |
| Baidu — fp8 | $0.44 | $1.32 |
| AtlasCloud — fp4 | $0.44 | $1.32 |
| Cloudflare | $0.44 | $1.32 |
DeepSeek V4 Flash 0731 head to head
Common questions about DeepSeek V4 Flash 0731 pricing
- How much does DeepSeek V4 Flash 0731 cost?
- DeepSeek V4 Flash 0731 costs $0.07 per million input tokens and $0.18 per million output tokens on the API.
- Does DeepSeek V4 Flash 0731 offer batch or cached pricing?
- Prompt-cache reads cost $0.02/M input tokens. No batch pricing is published.
- What would DeepSeek V4 Flash 0731 cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, DeepSeek V4 Flash 0731 costs about $19 at list prices.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for DeepSeek V4 Flash 0731 in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server