DeepSeek V4 Flash 0731 (batch) API Pricing
DeepSeek · context window 1M · prices updated 2026-09-15
Where DeepSeek V4 Flash 0731 (batch) sits on price
At $0.33 per million output tokens, DeepSeek V4 Flash 0731 (batch) is a budget tier model — 6.3× cheaper than the median output price of $2.08, which puts it cheaper than 86% and pricier than 14% of the models we track. It sits 4th cheapest of the 18 DeepSeek models we track. Output is only 3.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.
Cached input is 97% cheaper. On an input-heavy workload you need roughly a 26% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on DeepSeek V4 Flash 0731 (batch)
These three workloads are the ones teams actually run on a budget-priced model — a $0.33/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. | $0.0001 | $304 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0001 | $3.13 |
| Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. | $0.0288 | $173 |
Model your exact traffic in the API cost calculator — it preloads DeepSeek V4 Flash 0731 (batch) with caching and batch options.
DeepSeek V4 Flash 0731 (batch) price history
DeepSeek last raised DeepSeek V4 Flash 0731 (batch)'s output price on Sep 9, 2026 (+18% per output token), from $0.14/$0.28 to $0.11/$0.33 per 1M in/out. That is the only repricing in the 18 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 28, 2026 (tracking began) | $0.14 | $0.28 | — |
| Sep 9, 2026 | $0.11 | $0.33 | +18% |
Change-points from our daily price snapshots (tracking since Aug 28, 2026; intraday moves between snapshots are not captured).
DeepSeek V4 Flash 0731 (batch) vs Llama 3.2 3B Instruct
The closest-priced alternative from another vendor is Llama 3.2 3B Instruct (Meta) — priced within a rounding error on output, with $0.06 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Llama 3.2 3B Instruct pricing →Cheaper alternatives
More DeepSeek models
Frequently asked questions
› How much does the DeepSeek V4 Flash 0731 (batch) API cost?
DeepSeek V4 Flash 0731 (batch) costs $0.11 per million input tokens and $0.33 per million output tokens, with cached input at $0.0035 per million (97% cheaper). That works out to roughly 3,030,303 output tokens per dollar.
› What does the high-volume classification workload cost on DeepSeek V4 Flash 0731 (batch)?
High-volume classification — 200K requests/day (400 in / 20 out) costs about $0.0001 per request and $304 per month on DeepSeek V4 Flash 0731 (batch). Short output, huge volume: the input price dominates the bill.
› What does it cost to fill DeepSeek V4 Flash 0731 (batch)'s 1M context window?
Sending 1M of input in a single request costs $0.1153 at $0.11 per million tokens — before any output. With prompt caching that same fill drops to about $0.0037 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is DeepSeek V4 Flash 0731 (batch) worth the price?
DeepSeek V4 Flash 0731 (batch) is in the cheapest end of the market — cheaper than 86% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.