DeepSeek API pricing
15 models · CN
Open-weight reasoning and coding models priced far below Western equivalents, with off-peak discounts.
- Cheapest input / 1M
- $0.060
- Priciest input / 1M
- $1.60
- Largest context
- 1.3M
- Models tracked
- 15
DeepSeek V4 Flash 0731
DeepSeek V4 Pro 0423
DeepSeek V4 Flash 0731
All DeepSeek models
Cheapest first, by blended cost.
| # | Model | Blended / 1M | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|---|---|
| 1 | DeepSeek V4 Flash 0731 DeepSeek | $0.075 | $0.060 | $0.120 | 1.3M | ReasoningToolsOpen weights |
| 2 | DeepSeek V4 Flash 0423 DeepSeek | $0.107 | $0.086 | $0.171 | 1.0M | ReasoningToolsOpen weights |
| 3 | DeepSeek V4.1 Flash DeepSeek | $0.262 | $0.150 | $0.600 | 1.0M | ReasoningToolsVisionOpen weights |
| 4 | DeepSeek V3.2 DeepSeek | $0.302 | $0.269 | $0.400 | 164K | ReasoningToolsOpen weights |
| 5 | DeepSeek V3.2 Exp DeepSeek | $0.305 | $0.270 | $0.410 | 164K | ReasoningToolsOpen weights |
| 6 | DeepSeek V4 Flash Vision Exp DeepSeek | $0.330 | $0.220 | $0.660 | 1.0M | ReasoningToolsVisionOpen weights |
| 7 | DeepSeek V3.1 DeepSeek | $0.425 | $0.250 | $0.950 | 164K | ReasoningToolsOpen weights |
| 8 | DeepSeek V3 0324 DeepSeek | $0.438 | $0.250 | $1.00 | 164K | ToolsOpen weights |
| 9 | DeepSeek V3 DeepSeek | $0.450 | $0.257 | $1.03 | 164K | ToolsOpen weights |
| 10 | DeepSeek V3.1 Terminus DeepSeek | $0.453 | $0.270 | $1.00 | 164K | ReasoningToolsOpen weights |
| 11 | R1 Distill Llama 70B DeepSeek | $0.800 | $0.800 | $0.800 | 8K | ReasoningOpen weights |
| 12 | R1 0528 DeepSeek | $0.913 | $0.500 | $2.15 | 164K | ReasoningToolsOpen weights |
| 13 | R1 DeepSeek | $1.15 | $0.700 | $2.50 | 64K | ReasoningToolsOpen weights |
| 14 | DeepSeek V4 Pro 0813 DeepSeek | $1.48 | $0.983 | $2.95 | 1.0M | ReasoningToolsOpen weights |
| 15 | DeepSeek V4 Pro 0423 DeepSeek | $2.00 | $1.60 | $3.20 | 1.0M | ReasoningToolsOpen weights |
Frequently asked
How much does the DeepSeek API cost?
DeepSeek models in this directory range from $0.060 to $1.60 per million input tokens. The cheapest is DeepSeek V4 Flash 0731; the most expensive is DeepSeek V4 Pro 0423.
How many models does DeepSeek offer?
15 models are tracked here, with the largest context window being 1.3M tokens on DeepSeek V4 Flash 0731.