DeepSeek V3.2
DeepSeekDeepSeek's general-purpose model, priced well below most flagship alternatives.
Main uses: Cost-sensitive production workloads - chat, summarization, extraction - where text-only input is enough.
What sets it apart: At $0.259/$0.80 per 1M tokens, roughly 8× cheaper than Claude Sonnet 5 on output.
In
$0.26
Out
$0.38
Blended
$0.29
Where to buy this model
9 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.21 | $0.31 | $0.23 | - | |
| $0.26 | $0.38 | $0.29 | +26% | |
| ● AtlasCloud fp8 | $0.26 | $0.38 | $0.29 | +26% |
| ● Baidu fp8 | $0.28 | $0.42 | $0.32 | +39% |
| ● SiliconFlow fp8 | $0.26 | $0.80 | $0.39 | +70% |
| $0.30 | $0.96 | $0.47 | +104% | |
| ● Phala | $1.00 | $1.00 | $1.00 | +335% |
| ● Mara | $3.00 | $4.50 | $3.38 | +1370% |
| $3.00 | $4.50 | $3.38 | +1370% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 164K
- max output
- 147K
- cache read /1M
- $0.13
- Family
- deepseek
- Modalities
- text
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
DeepSeek models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| DeepSeek V3.2 · this model | $0.26 | $0.38 | 164K |
| DeepSeek V3.2 Exp | $0.27 | $0.41 | 164K |
| DeepSeek V4 Flash Vision Exp | $0.216 | $0.647 | 1.048576M |
| DeepSeek V3.1 | $0.25 | $0.95 | 164K |
| DeepSeek V3 | $0.257 | $1.03 | 164K |
| DeepSeek V3.1 Terminus | $0.27 | $1 | 164K |