DeepSeek V4 Flash
$0.14
Input / MTok
$0.28
Output / MTok
$0.0028
Cache read / MTok
Moving to peak/off-peak billing 2026-08-16; see scheduled_change.
API identifier deepseek-v4-flash · Context 1,000,000 tokens · Max output 384,000
· vendor pricing page
Scheduled change · 0 days away
On 16 August 2026 pricing moves to $0.22 input / $0.66 output per million tokens. DeepSeek moves to peak/off-peak billing at 16:00 UTC. Off-peak (majority of hours) rate shown here; peak hours 01:00-04:00 and 06:00-10:00 UTC bill at $0.44 input / $1.32 output / $0.014 cache-read, double the off-peak rate..
Full price sheet
| Metric | USD / million tokens |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
| Cache read | $0.0028 |
Price history
| Observed | Metric | Price |
|---|---|---|
| 2026-08-07 12:06:21 | Input | $0.14 |
| 2026-08-07 12:06:21 | Output | $0.28 |
| 2026-08-07 12:06:21 | Cache read | $0.0028 |
Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.
Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| DeepSeek V4 Flash (0731) | $0.14 | $0.28 | compare → |
| DeepSeek V4 Flash | $0.14 | $0.28 | compare → |
| GPT-OSS 20B | $0.075 | $0.3 | compare → |
| GPT-OSS 20B | $0.07 | $0.3 | compare → |
| Qwen3.5 9B | $0.17 | $0.25 | compare → |
| Ministral 3 14B | $0.2 | $0.2 | compare → |