DeepSeek
DeepSeek: DeepSeek V3.2
deepseek/deepseek-v3.2-20251201Hugging Face ↗
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...
DeepSeek: DeepSeek V3.2 usage over time
OpenRouter share of tokens, by day.
DeepSeek: DeepSeek V3.2 holds 0.54% today, down from 2.75% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
DeepSeek: DeepSeek V3.2's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-07-14, DeepSeek: DeepSeek V3.2 holds 0.5% of OpenRouter token share, down 2.29pp over 30 days. Source: Tidelines (OpenRouter).
Where to run it
Providers & pricing
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| StreamLake | $0.21 | $0.32 | 128k | 95.71% |
| Baidu | $0.25 | $0.38 | 131k | 99.98% |
| DeepInfra | $0.26 | $0.38 | 164k | 99.12% |
| AtlasCloud | $0.26 | $0.38 | 164k | 99.94% |
| Novita | $0.27 | $0.40 | 164k | 99.97% |
| SiliconFlow | $0.26 | $0.42 | 164k | 99.03% |
| GMICloud | $0.29 | $0.43 | 164k | 99.90% |
| Venice | $0.33 | $0.48 | 160k | 98.18% |
| Phala | $1.00 | $1.00 | 164k | 96.71% |
| Alibaba | $0.37 | $1.11 | 131k | 95.36% |
| DigitalOcean | $0.42 | $1.36 | 164k | 94.70% |
| Friendli | $0.50 | $1.50 | 164k | 99.97% |
| $0.56 | $1.68 | 164k | 99.81% | |
| SambaNova | $3.00 | $4.50 | 33k | — |