DeepSeek: DeepSeek V3.2
deepseek/deepseek-v3.2
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...
Modalities
In / Out Price
$0.259 / $0.42 per 1M
Context
164K
Released
Dec 1, 2025
Knowledge Cutoff
—
Uptime
Share of successful requests per carrier, measured over the last 5 minutes, 30 minutes and day. When one carrier dips, the router fails over to the next.
Carriers
13
Best carrier, 30m
100.00%
Healthy now
11 / 13
| Provider | Status | Last 5m | Last 30m | Last day |
|---|---|---|---|---|
 GMICloud | Degraded | 100.00% | 100.00% | 98.40% |
 SiliconFlow | Operational | 100.00% | 100.00% | 93.26% |
 DeepInfra | Operational | 100.00% | 100.00% | 99.93% |
 AtlasCloud | Degraded | 100.00% | 100.00% | 97.01% |
 Venice | Operational | 100.00% | 100.00% | 99.51% |
 Baidu | Operational | 100.00% | 100.00% | 100.00% |
 DigitalOcean | Operational | 100.00% | 100.00% | 92.36% |
 Alibaba | Operational | 100.00% | 100.00% | 97.43% |
 Friendli | Operational | 100.00% | 100.00% | 100.00% |
 Google | Operational | 100.00% | 100.00% | 99.58% |
 Phala | Operational | — | 100.00% | 99.23% |
 Mara | Operational | — | — | 55.00% |
 SambaNova | Operational | 100.00% | 100.00% | 88.38% |