DeepSeek V4-Pro vs DeepSeek V4-Flash
DeepSeek's DeepSeek V4-Pro and DeepSeek's DeepSeek V4-Flash both target production language workloads, but they price and behave differently. Here is the side-by-side.
Pricing checked against provider documentation on . How we verify
The short answer
DeepSeek V4-Flash is the cheaper option — roughly 3.0x less on a blended workload, and it suits the cheapest capable open-weight option. DeepSeek V4-Pro justifies its premium when you need frontier-adjacent reasoning at open-weight prices.
DeepSeek • DeepSeek V4
$0.66 / $1.98
/ 1M tokens (input / output)
A 1.6T-parameter mixture-of-experts model with 49B active, released under MIT and callable through DeepSeek's own API with configurable reasoning effort. Since 16 August 2026 DeepSeek bills on a peak/off-peak schedule, so the hour you run a job changes the bill by exactly 2x — which makes it unusually well suited to scheduled batch work.
DeepSeek • DeepSeek V4
$0.22 / $0.66
/ 1M tokens (input / output)
A 284B-parameter MoE with only 13B active, which is why it runs fast and prices low. Notable for a 384K maximum output — far beyond the 128K most frontier models cap at — and for supporting both thinking and non-thinking modes, so you can switch reasoning off on easy requests rather than paying for it.
Input price
DeepSeek V4-Flash is 67% cheaper than DeepSeek V4-Pro on input tokens.
Output price
DeepSeek V4-Flash is 67% cheaper than DeepSeek V4-Pro on output tokens — usually the side that dominates the bill.
Monthly cost at three workload sizes
Standard (non-batch, non-cached) rates. Reasoning models will exceed these figures because thinking tokens bill as output.
| Workload | DeepSeek V4-Pro | DeepSeek V4-Flash | Difference |
|---|---|---|---|
| Light — 1M in / 200K out | $1 | $0 | $1 |
| Moderate — 10M in / 2M out | $11 | $4 | $7 |
| Heavy — 100M in / 20M out | $106 | $35 | $70 |
Specification comparison
| Attribute | DeepSeek V4-Pro | DeepSeek V4-Flash |
|---|---|---|
| Input (/ 1M tokens) | $0.66 | $0.22 |
| Output (/ 1M tokens) | $1.98 | $0.66 |
| Cached input | $0.02 | $0.01 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Max output | 131,072 tokens | 384,000 tokens |
| Native reasoning | Yes | Yes |
| Knowledge cutoff | 2026-03 | 2026-03 |
| Relative latency | medium | low |
| Open weights | MIT | MIT |
| API model ID | deepseek-v4-pro | deepseek-v4-flash |
| Status | stable | stable |
DeepSeek V4-Pro: Off-peak rate shown. Peak rates are exactly double ($1.32 input / $3.96 output) during 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday. Cache hits cost roughly 3% of a cache miss.
DeepSeek V4-Flash: Off-peak rate shown. Peak rates double ($0.44 / $1.32) during 01:00–04:00 and 06:00–10:00 UTC on weekdays. Superseded the earlier flat-rate pricing of $0.14 / $0.28 that many comparison sites still quote.
Choose DeepSeek V4-Pro if…
- Overnight batch reasoning jobs
- Self-hosted deployments needing MIT terms
- Cost-sensitive coding agents
- Chinese-language workloads
Choose DeepSeek V4-Flash if…
- High-volume classification and extraction
- Very long generated outputs
- Budget coding agents
- Local deployment on modest hardware
Frequently asked
Is DeepSeek V4-Pro or DeepSeek V4-Flash cheaper?
DeepSeek V4-Flash is cheaper. On a blended 3:1 input-to-output workload it costs about 3.0x less than DeepSeek V4-Pro.
Which has the larger context window, DeepSeek V4-Pro or DeepSeek V4-Flash?
Both accept up to 1M tokens, so context is not a differentiator here.
Should I use DeepSeek V4-Pro or DeepSeek V4-Flash?
Pick DeepSeek V4-Pro for frontier-adjacent reasoning at open-weight prices. Pick DeepSeek V4-Flash for the cheapest capable open-weight option. If cost dominates the decision, DeepSeek V4-Flash wins; if you need the capability ceiling, benchmark both on your own evals before committing.