Home › Models › DeepSeek V4.1 Flash
DeepSeek V4.1 Flash API pricing
DeepSeek V4.1 Flash is a model from DeepSeek with a 1,100,000-token context window. Rates below are per 1,000,000 tokens, verified October 2026.
Price list
| Token class | Rate / 1M | Notes |
|---|---|---|
| Input | $0.30 | Prompt tokens not served from cache |
| Cached input | $0.006 | 98% below base input |
| Cache write | — | Not billed per token |
| Output | $1.20 | 4.0× the input rate |
| Batch API | Not offered | No asynchronous tier |
Open weights. Peak rates; off-peak is half. No batch tier.
What DeepSeek V4.1 Flash costs at three real workloads
Sticker prices rarely match the invoice. These three workloads use the rates above, with cache writes charged once per job and the batch discount applied only where the provider offers it.
| Workload | Requests | Tokens | Estimated cost |
|---|---|---|---|
| Support chat | 1,000 | 4K in / 600 out | $1.92 |
| RAG with caching | 1,000 | 50K in (45K cached) / 1K out | $2.98 |
| Nightly batch job | 10,000 | 10K in / 2K out | $54 |
Caching the 45K-token prefix saves about 82% on the RAG workload versus sending it uncached every call ($16.20 → $2.98). With no batch tier, the nightly job bills at list price — schedule it for off-peak hours if the provider offers that.
Where DeepSeek V4.1 Flash sits in the market
Out of 28 models in this dataset, DeepSeek V4.1 Flash ranks #5 cheapest by input rate, #3 by output rate, and #4 on a blended 1M-input-plus-250K-output workload.
| Model | Provider | Input | Output | Blended |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $1.20 | $0.60 |
| GPT-5.4 nano | OpenAI | $0.20 | $1.25 | $0.512 |
| Gemini 3.5 Flash-Lite | Google Gemini | $0.30 | $2.50 | $0.925 |
| GPT-5.6 Luna | OpenAI | $0.20 | $1.20 | $0.50 |
Blended cost = 1M input tokens + 250K output tokens at list price.
FAQ
How much does DeepSeek V4.1 Flash cost per 1M tokens?
$0.30 per 1M input tokens and $1.20 per 1M output tokens on the standard tier.
Is prompt caching cheaper on DeepSeek V4.1 Flash?
Yes. Cached input bills at $0.006 per 1M tokens, 98.0% below the $0.30 base input rate, with no separate cache-write rate published.
Does DeepSeek V4.1 Flash support the Batch API?
No. DeepSeek publishes no batch tier for DeepSeek V4.1 Flash; off-peak hours bill at half the peak rate instead.