R1 0528 (DeepSeek) and DeepSeek V4 Pro 0813 (DeepSeek) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.
Snapshot as of 24 October 2026
As of 24 October 2026, DeepSeek V4 Pro 0813 holds the stronger ModelCap Index position (#31 vs #80); DeepSeek V4 Pro 0813 is cheaper per output token ($1.98/1M vs $2.15/1M); and DeepSeek V4 Pro 0813 offers the longer context window (1M vs 164K tokens).
Evidence: 2 public benchmark observations across 2 boards · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.
Benchmark scores: R1 0528 vs DeepSeek V4 Pro 0813
Public benchmark boards where R1 0528 or DeepSeek V4 Pro 0813 has a published result
DeepSeek V4 Pro 0813 ranks higher on the ModelCap Index as of 24 October 2026: #31 against #80. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.
Is R1 0528 cheaper than DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 is cheaper on output tokens: $1.98/1M against $2.15/1M. Input tokens are $0.50/1M for R1 0528 and $0.66/1M for DeepSeek V4 Pro 0813. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $2.08 for R1 0528 versus $2.31 for DeepSeek V4 Pro 0813. R1 0528 costs 10.2% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.
Which has the bigger context window, R1 0528 or DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 has the larger context window: 1M tokens against 164K. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified.
Which is better for coding, R1 0528 or DeepSeek V4 Pro 0813?
Arena coding: R1 0528 1464, DeepSeek V4 Pro 0813 1505 — DeepSeek V4 Pro 0813 leads.
Are R1 0528 and DeepSeek V4 Pro 0813 open-weight models?
R1 0528: Open weights. DeepSeek V4 Pro 0813: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence. A missing weight link does not identify every API or chat product that offers a model.
Where can I run R1 0528 and DeepSeek V4 Pro 0813?
ModelCap currently lists 3 API providers for R1 0528 and 21 for DeepSeek V4 Pro 0813, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.
How current is this R1 0528 vs DeepSeek V4 Pro 0813 comparison?
Every figure and ModelCap Index position comes from the same published snapshot dated 24 October 2026. Publication and page updates happen separately; use the snapshot date shown on the page.