deepseek-v4-pro API Pricing
deepseek-v4-pro on DeepSeek costs $1.32 per 1M input tokens and $3.96 per 1M output tokens (as of ).
| Input | $1.32 / 1M tokens |
|---|---|
| Output | $3.96 / 1M tokens |
| Cached input (read) | $0.04 |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 1M tokens |
| Max output | 393K tokens |
| Supports | tool calling, reasoning, prompt caching |
| Deprecation date | None listed |
| API model id | deepseek-v4-pro |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $4.62 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $7.00 |
| 1 million classification calls (300 in, 5 out each) | $415.80 |
Try your own numbers in the LLM API cost calculator.
Price history
- Between and : cached input price changed from $0.0036 to $0.04 per 1M tokens.
- Between and : output price changed from $0.87 to $3.96 per 1M tokens.
- Between and : input price changed from $0.43 to $1.32 per 1M tokens.
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| deepseek-r1 | DeepSeek | $0.55 | $2.19 | $0.14 | 66K |
| deepseek-flash | DeepSeek | $0.30 | $1.20 | $0.006 | 1M |
| deepseek-v4-flash | DeepSeek | $0.30 | $1.20 | $0.006 | 1M |
| deepseek-v4-flash-vision-exp | DeepSeek | $0.30 | $1.20 | $0.006 | 1M |
| deepseek-v3 | DeepSeek | $0.27 | $1.10 | $0.07 | 66K |
| deepseek-chat | DeepSeek | $0.28 | $0.42 | $0.03 | 131K |
| deepseek-reasoner | DeepSeek | $0.28 | $0.42 | $0.03 | 131K |
| deepseek-v3.2 | DeepSeek | $0.28 | $0.40 | $0.03 | 164K |