Model pricing · DeepSeek
DeepSeek V4 Flash pricing
DeepSeek V4 Flash costs $0.14 per million input tokens and $0.28 per million output tokens at list price. Best for: extreme price-performance.
| Input | $0.14 / 1M tokens |
|---|---|
| Output | $0.28 / 1M tokens |
| Cached input (read) | $0.0028 / 1M tokens |
| Context window | 1,000,000 tokens |
Cache-hit as printed on provider page (aggregators show higher).
Source: DeepSeek pricing, cross-checked against models.dev on 2026-09-15. Your provider invoice is authoritative.
What it costs in practice
| Workload | List price | If input is cached |
|---|---|---|
| One request: 10,000 tokens in, 1,000 out | $0.0017 | $0.0003 |
| A month of that request, 100 times a day | $5.04 | $0.924 |
| A 3,000-token instruction file on 100 requests a day, for a month | $1.26 | $0.025 |
The last row is the always-on cost of an instruction file like CLAUDE.md: paid on every request, whether the task needs it or not. Check how much of yours is waste.
Price history
From tokencheat's dated pricing snapshots. Only changes are listed.
| Since | Input / 1M | Output / 1M |
|---|---|---|
| 2026-01-01 | $0.14 | $0.28 |
Similarly priced models
Cohere Command R (08-2024)
$0.15 in · $0.6 out · Cohere
Llama 4 Maverick
$0.15 in · $0.6 out · Meta (via OpenRouter)
Mistral Small 4
$0.15 in · $0.6 out · Mistral
Gemini 2.5 Flash-Lite
$0.1 in · $0.4 out · Google
Compare every model side by side or price your own workload.