Router DeskHomeDeepSeek R1 0528
DeepSeek R1 0528
R1 0528 is the May 2025 reasoning snapshot. It costs more per token than V4 Flash and answers more slowly when reasoning is on.
Updated 2026-09-27
The slug is deepseek/deepseek-r1-0528. On 27 Sep 2026 four endpoints were listed: DeepInfra at $0.50 input and $2.15 output per million, SiliconFlow at $0.50 and $2.18, StreamLake at $0.571 and $2.286 with a 128,000-token window, and Novita at $0.70 and $2.50. The larger windows on the first two were 163,840 tokens.
Reasoning tokens are billed as output. A short visible answer can still be a long bill if the trace is long. V4 Pro is the newer place OpenRouter points people who want reasoning plus a million-token window. Stay on R1 0528 when you are comparing an old eval.
Prices are pass-through. A provider marked degraded on the model page should not be treated as the rate you will actually get.
Questions
What is the model id for DeepSeek R1 0528?
deepseek/deepseek-r1-0528
How much does R1 0528 cost?
About $0.50 to $0.70 per million input tokens and $2.15 to $2.50 per million output tokens, depending on the provider row checked on 27 Sep 2026.
Should new projects use R1 or V4?
New projects should start from a V4 slug. R1 0528 remains useful when a result has to match that snapshot.
Related
- DeepSeek API price
On 27 Sep 2026 OpenRouter listed DeepSeek V4 Pro 0423 at $0.348 / $0.696 per million tokens, and V4 Pro 0813 at $0.245 / $3.50.
- DeepSeek on OpenRouter
OpenRouter lists several DeepSeek slugs at once: V4 Pro, V4 Flash, older V3 chats, and R1 0528. The slug in your request picks the price.
- DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus was about $0.27 per million input tokens on healthy endpoints on 27 Sep 2026. Two of four providers were not in service.
- Coding models
Coding-model choice on OpenRouter is price, context, and tool-call reliability. DeepSeek V4, Qwen3.7 Max, GLM 5.2, and Sonnet 5 are the slugs to price first.