DeepSeek V3.2 Exp
MoE workstation685B total, ~37B active per token (MoE, 256 routed experts) - shares the V3 backbone. Adds DeepSeek Sparse Attention (DSA): a lightning indexer (FP8, Hadamard dot-product) selects top-2048 tokens per query, then MLA runs only over those. The first fine-grained sparse attention from DeepSeek and the precursor to V4’s CSA.
Built on V3.1-Terminus. Experimental; superseded by V4 within ~7 months. Open weights under MIT.
AI-generated content marks
This model embeds text watermarks in generated text and adds C2PA provenance metadata to supported files such as .png, .jpg, and .svg. Marks can be lost through editing, screenshots, or format conversion, so their absence does not prove a file is human-made.
- 685.0B
- 128k
- mit
- 🇨🇳 China
- Sep 2025
Scores
Score per dollar
307 pts per $/M input
general_score (83) divided by cheapest input price ($0.27/M). Higher is better value. See live pricing.
Related models
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Or run it in the cloud
Live per-provider pricing, throughput and uptime - refreshed about 3 hours ago via OpenRouter. Click a column to sort.
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
SiliconFlow
|
API | 0.27 | 0.41 | - | - | - | 99.91% | best uptime |
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
Detailed API pricing page + JSON endpoint →
See who runs DeepSeek in production →
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.