DeepSeek V4 Pro
MoE premier1.6T total, 49B active per token (MoE). Hybrid attention: Compressed Sparse Attention (CSA, 4x KV compression) + Heavily Compressed Attention (HCA, 128x) across 61 layers, manifold-constrained Hyper-Connections (mHC). FP4 experts + FP8 rest, 32T+ pretraining tokens, Muon optimizer.
- Context: 1M native; Think Max mode recommends >=384K.
- Self-hosting: ~800GB+ for Q4 weights - needs a multi-H200/H100 cluster or DGX-class system. Not workstation-fittable, so cloud-only for nearly everyone despite the open weights.
Top open-weight agentic coding score (SWE-bench Verified 80.6). Open weights under MIT.
API phase-out (announced 2026-09-09): from 2026-09-14 04:00 UTC, deepseek-v4-pro requests route to DeepSeek V4.1 Flash at Flash rates (previously $1.32 peak in / $3.96 peak out per 1M) until V4.1-Pro launches.
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.
- 1600.0B
- 1000k
- mit
- 🇨🇳 China
- Apr 2026
Benchmark scores
Vendor-reported - from the developer's own model card / tech report
Vendor-reported - from the developer's own model card / tech report
Ran this model on your own hardware? Join free and add your measured tok/s to the community numbers.
Score per dollar
297 pts per $/M input
general_score (89) divided by cheapest input price ($0.30/M). Higher is better value. See live pricing.
Related models
Guides covering DeepSeek V4 Pro
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 9 hours ago via OpenRouter. Click a column to sort.
some pricing may be stale - last verified 2026-10-09
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
Relace
|
API | 0.30 | 4.20 | 0.230 | - | - | 100.00% | best uptime |
|
Nous Portal
stale
|
API | 0.53 | 1.58 | - | - | - | - | |
|
StreamLake
|
API | 0.96 | 1.91 | 0.080 | - | - | 100.00% | |
|
GMICloud
|
API | 0.96 | 1.91 | 0.080 | - | - | 100.00% | |
|
DigitalOcean
|
API | 1.04 | 2.09 | 0.209 | - | - | 100.00% | |
|
Reka
|
API | 1.05 | 10.50 | 0.210 | - | - | 100.00% | |
|
Cloudflare
|
API | 1.15 | 2.55 | 0.200 | - | - | 100.00% | |
|
DeepInfra
|
API | 1.30 | 2.60 | 0.100 | - | - | 100.00% | |
|
Alibaba
|
API | 1.42 | 2.83 | 0.118 | - | - | 100.00% | |
|
SiliconFlow
|
API | 1.50 | 3.14 | 0.135 | - | - | 100.00% | |
|
Novita
|
API | 1.60 | 3.20 | 0.135 | - | - | 100.00% | |
|
Venice
|
API | 1.65 | 3.30 | 0.330 | - | - | 100.00% | |
|
AtlasCloud
|
API | 1.68 | 3.38 | 0.130 | - | - | 100.00% | |
|
Baidu
|
API | 1.69 | 3.38 | 0.140 | - | - | 100.00% | |
|
Azure
|
API | 1.91 | 3.83 | 0.160 | - | - | 100.00% | |
|
Parasail
risky
|
API | 0.45 | 3.48 | 0.100 | - | - | 93.33% | |
| Sub | - | - | - | - | - | - | $10.00/mo Go ($5 first month) |
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.