Models · DeepSeek
DeepSeek V4 Pro 0813
Asked for a few hundred random integers, DeepSeek V4 Pro 0813 does not pick evenly. This page is the shape of that preference, built from 36 recorded answers containing 10584 numbers, and it is what the identify tool compares a pasted reply against.
- Bank id
deepseek-v4-pro-0813@openrouter:deepseek- Family
- DeepSeek
- Collected through
- OpenRouter
- Collected on
- 2026-09-18
- Status
- Collected by this project
- Distinct values used
- 355 of 355
- Prompt environments
- 12 of 12
Capability and price
- Sold by
- DeepSeek
- Intelligence index
- 36 · v4.3.2, scored as reasoning, max effort
- Index rank
- 10 of 11
- Input, per 1M tokens
- 1.32
- Output, per 1M tokens
- 3.96
- Blended, per 1M tokens
- 1.98
- Price rank
- 3 of 11
- Context window
- 1,000,000 tokens
The provider's standard rate. Off-peak hours are billed at half of it.
Read on 2026-09-23, not measured here: index page · price page
Distribution
Every bar is one value from 1 to 355; its height is how many times the model chose it across all recorded answers. A perfectly random picker would give a flat line. Nothing in the bank does.
Favourite numbers
| Number | Times chosen | Share |
|---|---|---|
| 349 | 50 | 0.47% |
| 310 | 49 | 0.46% |
| 352 | 48 | 0.45% |
| 354 | 45 | 0.43% |
| 318 | 44 | 0.42% |
| 338 | 44 | 0.42% |
| 347 | 44 | 0.42% |
| 337 | 43 | 0.41% |
| 342 | 43 | 0.41% |
| 118 | 42 | 0.40% |
| 309 | 42 | 0.40% |
| 322 | 42 | 0.40% |
How reliably it is recognised
In held-out testing across all twelve prompt environments, 4 of 12 three-answer runs named this model with a clear margin, 1 were close calls inside its family, 7 had only a weak match, and 0 named a different model with a clear margin.
With this model removed from the bank and its own answers scored against the rest, 0 of 12 runs still named another model with a clear margin, 0 were close calls inside the family, and 12 had only a weak match. Its answers landed most often on Qwen3.8 Max 0902 (6 of 12). That is the number to keep in mind if you are testing a version that is not listed here.
Fresh holdout on the site's nine prompts, identical on the API and chat input paths: with the previous bank, top-1/Clear were 0/9 and 0/9 for both models; with this bank, DeepSeek reaches 8/9 and 4/9 for single replies and 3/3 and 1/3 for the three environment groups, and Qwen reaches 9/9 and 9/9 for single replies (every reply Clear) and 3/3 and 3/3 for the groups. Collected through OpenRouter with the serving provider pinned; identity is declared provenance, not an independent attestation.
Both measurements count the status the site attaches to the first-ranked model, not the bare ranking alone. The methodology page explains how they were made and what they leave out.