DeepSeek V4 Flash pricing
DeepSeek ·
deepseek-deepseek-v4-flash ·
1M context
· 2nd cheapest of 64 current models
What DeepSeek V4 Flash costs
| Rate | Per 1M tokens | Per 1K tokens | What it covers |
|---|---|---|---|
| Input | $0.14 | $0.00014 | Every token you send: prompt, history, documents. |
| Output | $0.28 | $0.00028 | Every token the model generates, including hidden reasoning tokens. |
| Cached input | $0.0028 | $0.0000028 | Input served from the provider’s prompt cache. |
What that means in practice
The same three workloads are costed on every model page, so these numbers are directly comparable across the catalog. No prompt caching and no batch discount is assumed — the figures are what you pay before you optimise anything.
Support chatbot
2,500 six-turn conversations a day
$394 / month
$0.0053 per conversation · $4,791 a year
An 800-token system prompt, 400-token questions and 900-token answers, over six turns — each turn re-sending everything before it.
Document summariser
1,000 single-shot summaries a day
$57.96 / month
$0.0019 per conversation · $705 a year
One 12,000-token document in, an 800-token summary out, no conversation history. The case where input dominates the bill.
Coding agent
200 twelve-turn sessions a day
$318 / month
$0.053 per conversation · $3,863 a year
A 3,000-token system prompt, 1,500-token instructions and 2,500-token responses over twelve turns. Long sessions are where the quadratic cost of re-sent history stops being theoretical.
Change the assumptions in the calculator
Cheaper models in the catalog
Nothing cheaper is scored as highly as DeepSeek V4 Flash, so these are simply the cheaper options, best-scored first. Trading down here is a real trade.
| Model | Input | Output | Blended saving | |
|---|---|---|---|---|
| GPT-5 Nano | $0.05 | $0.4 | 21% |
Head to head
- DeepSeek V4 Flash vs Qwen3 Next 80B
- DeepSeek V4 Flash vs GPT-5.6 Luna
- DeepSeek V4 Flash vs Grok 4.1 Fast
Specification
| Context window | 1M tokens |
|---|---|
| Maximum output | 8K tokens |
| Provider | DeepSeek |
| Status | Current |
| Reasoning model | Yes |
| Vision | No |
| Token counting | Estimated at ~3.4 characters per token (Estimate — DeepSeek's tokenizer handles Chinese far more densely than English) |
Where these numbers come from
Last checked against its source on 2026-08-02, and the published rates last actually moved on 2026-08-02. Source of record: LiteLLM’s community-maintained price map.
Regional and data-residency premiums, priority tiers, server-side tool fees and negotiated discounts are not included. Prices change without notice; this page is rebuilt every time the catalog does.