DeepSeek V4 Provso1
DeepSeek V4 Pro is cheaper than o1 at $1.74/M vs $15/M input tokens.
| Spec | DeepSeek V4 Pro | o1 |
|---|---|---|
| Input price | $1.74/M tokens | $15/M tokens |
| Output price | $3.48/M tokens | $60/M tokens |
| Context window | 1.0M tokens | 128K tokens |
| Weights | Open | Closed |
| Free API (OpenRouter) | No | No |
| Released | Apr 2026 | Dec 2024 |
Our Verdict
DeepSeek V4 Pro
o1Runner-up
Not enough votes to call it. On the specs, DeepSeek V4 Pro has the edge: bigger model tier, newer, bigger context window.
DeepSeek V4 Pro costs 17x less per token.
Slight edge
Reviewing agent-written code?See a Brief PR report
API pricing
Cost per 1M tokens
DeepSeek V4 Pro
Input
$1.74
8.6× cheaper
Output
$3.48
17× cheaper
o1
Input
$15.00
Output
$60.00
DeepSeek V4 Pro is cheaper on both: 8.6× input, 17× output.
Where to run it
15 hosts, cheapest first
DeepSeek V4 Pro14 hosts
StreamLakefp8$0.65 in$1.29 out1M98.6% upBaidu Qianfanfp8$0.66 in$1.31 out1M100% upDigitalOcean$0.87 in$1.74 out1M100% upGMI Cloudfp8$0.96 in$1.91 out1M99.7% upDeepInfrafp8$1.30 in$2.60 out1M99.5% upAlibaba Cloudfp8$1.42 in$2.83 out1M100% up
8 more hostsFewer hosts
SiliconFlowfp8$1.50 in$3.13 out1M98.4% upNovitafp8$1.60 in$3.20 out1M100% upVenice$1.65 in$3.30 out1M98.4% upAtlasCloudfp4$1.68 in$3.38 out1M99.3% upBasetenfp4$1.74 in$3.48 out1M99.8% upParasailfp8$1.74 in$3.48 out1M99.8% upAzure AI Foundry$1.91 in$3.83 out1M99.3% upNextBitfp8$2.00 in$4.00 out1M99.9% up
Per million tokens. Prices and uptime via OpenRouter, checked 13 Sep 2026.
Writing DNA
Style Comparison
Similarity
63%
DeepSeek V4 Pro uses 3.5x more emoji
DeepSeek V4 Pro
o1
57%Vocabulary65%
18wSentence Length16w
0.52Hedging0.81
3.3Bold3.6
2.3Lists2.1
0.04Emoji0.00
0.45Headings0.32
0.15Transitions0.29
Based on 27 + 18 text responses
Research
What we learned reading every model
FAQ
