DeepSeek V4 Flash
$0.14
Input / MTok
$0.28
Output / MTok
$0.028
Cache read / MTok
Hosted third-party inference; price is Fireworks' Standard serverless rate, not DeepSeek's own API. Optional Priority tier at 1.5x.
API identifier accounts/fireworks/models/deepseek-v4-flash
· vendor pricing page
Full price sheet
| Metric | USD / million tokens |
|---|---|
| Input | $0.14 |
| Output | $0.28 |
| Cache read | $0.028 |
Price history
| Observed | Metric | Price |
|---|---|---|
| 2026-08-08 07:26:49 | Input | $0.14 |
| 2026-08-08 07:26:49 | Output | $0.28 |
| 2026-08-08 07:26:49 | Cache read | $0.028 |
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.
Changes affecting this model
coverage
DeepSeek V4 Flash added to coverage
—
2026-08-08Compare with
Models at a similar price point.
| Model | Input | Output | |
|---|---|---|---|
| DeepSeek V4 Flash | $0.14 | $0.28 | compare → |
| DeepSeek V4 Flash (0731) | $0.14 | $0.28 | compare → |
| GPT-OSS 20B | $0.075 | $0.3 | compare → |
| GPT-OSS 20B | $0.07 | $0.3 | compare → |
| Devstral Small 2 | $0.1 | $0.3 | compare → |
| Qwen3.5 9B | $0.17 | $0.25 | compare → |