R1 0528 pricing & benchmarks
R1 0528 is available from DeepSeek at $0.500 per million input tokens and $2.15 per million output tokens ($0.912 blended at 3:1). It accepts up to 163,840 tokens of context. May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
Pricing
Per million tokens · OpenRouter
Input$0.500
Output$2.15
Blended (3:1)$0.912
Specification
deepseek/deepseek-r1-0528
Context window164K
Max output33K
ReleasedMay 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for R1 0528 yet. We show nothing rather than reprinting an unverified figure.
Where to run R1 0528
4 hosts · 1.3× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra | $0.913 | $0.500 / $2.15 | 164K | fp4 | 99.9% |
| SiliconFlow | $0.920 | $0.500 / $2.18 | 164K | fp8 | 99.5% |
| StreamLake ⚠ 128K context, not 164K |
$1.000 | $0.571 / $2.29 | 128K | — | 99.8% |
| Novita | $1.15 | $0.700 / $2.50 | 164K | fp8 | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare R1 0528
FAQ
How much does R1 0528 cost?
R1 0528 costs $0.500 per million input tokens and $2.15 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.912 per million tokens.
What is R1 0528's context window?
R1 0528 accepts up to 163,840 tokens of context, and can generate up to 32,768 output tokens.