DeepSeek V3.2
deepseek/deepseek-v3.2
- context
- 164K
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Low cost
Overview
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Providers
- AlibabaView Alibaba
- AtlasCloudView AtlasCloud
- BaiduView Baidu
- DeepInfraView DeepInfra
- DigitalOceanView DigitalOcean
- FriendliView Friendli
- GMICloudView GMICloud
- GoogleView Google
- MaraView Mara
- NovitaView Novita
- PhalaView Phala
- SambaNovaView SambaNova
- SiliconFlowView SiliconFlow
- StreamLakeView StreamLake
- VeniceView Venice
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibaba | $0.3705 | $1.1115 |
| AtlasCloud | $0.26 | $0.38 |
| Baidu | $0.28 | $0.42 |
| DeepInfra | $0.26 | $0.38 |
| DigitalOcean | $0.30 | $0.96 |
| Friendli | $0.50 | $1.50 |
| GMICloud | $0.2088 | $0.3096 |
| $0.56 | $1.68 | |
| Mara | $3.00 | $4.50 |
| Novita | $0.269 | $0.40 |
| Phala | $1.00 | $1.00 |
| SambaNova | $3.00 | $4.50 |
| SiliconFlow | $0.259 | $0.80 |
| StreamLake | $0.2145 | $0.3218 |
| Venice | $0.2683 | $0.3902 |
Alibaba
- input / 1M
- $0.3705
- output / 1M
- $1.1115
AtlasCloud
- input / 1M
- $0.26
- output / 1M
- $0.38
Baidu
- input / 1M
- $0.28
- output / 1M
- $0.42
DeepInfra
- input / 1M
- $0.26
- output / 1M
- $0.38
DigitalOcean
- input / 1M
- $0.30
- output / 1M
- $0.96
Friendli
- input / 1M
- $0.50
- output / 1M
- $1.50
GMICloud
- input / 1M
- $0.2088
- output / 1M
- $0.3096
Google
- input / 1M
- $0.56
- output / 1M
- $1.68
Mara
- input / 1M
- $3.00
- output / 1M
- $4.50
Novita
- input / 1M
- $0.269
- output / 1M
- $0.40
Phala
- input / 1M
- $1.00
- output / 1M
- $1.00
SambaNova
- input / 1M
- $3.00
- output / 1M
- $4.50
SiliconFlow
- input / 1M
- $0.259
- output / 1M
- $0.80
StreamLake
- input / 1M
- $0.2145
- output / 1M
- $0.3218
Venice
- input / 1M
- $0.2683
- output / 1M
- $0.3902
Use this model
through Nautili
Route requests to DeepSeek V3.2 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.