MoE workstation284B total, 13B active per token (MoE). Same FP4+FP8 hybrid-attention family as V4 Pro: Compressed Sparse Attention (CSA) + Heavily Compressed Attention (HCA) across 61 layers, manifold-constrained Hyper-Connections (mHC), Muon optimizer, 32T+ pretraining tokens. 1M native context, 384K max output; three modes (non-think / think-high / think-max). At ~150-170GB for Q4 weights it self-hosts on a 2x H100/H200 node, and at Q2 on a 192GB Mac Studio or 2x RTX 6000 Ada workstation. The model the deepseek-chat/reasoner API aliases now route to (retired 2026-07-24). Open weights under MIT.
- 284.0B
- 1000k
- mit
- Apr 2026
Scores #
Or run it in the cloud #
Live per-provider pricing, throughput and uptime - refreshed 3 days ago via OpenRouter. Click a column to sort.
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
| API | 0.09 | 0.18 | - | - | - | - | cheapest |
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 →
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.