modelgrep
D

DeepSeek: R1 0528

deepseek/deepseek-r1-0528

86th smartest of 180ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
27.1
86th of 180
Design Elo
1222
Data Viz
Speed
30
242nd fastest
Latency
627ms
first token
Input price
$0.500
164th cheapest
Context
164K
33K max out

How it compares

Smarter than52%
of all ranked models
Faster than21%
of all ranked models
Cheaper than45%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis48th percentile
Intelligence Index
27.1
Coding Index
24.0
Agentic Index
20.8
GPQA Diamond
81%
Humanity's Last Exam
15%
SciCode
40%
Tau²-Bench (agentic)
37%
Design Arena · Elo8,357 tournaments
Data Viz
1222
Website
1194
3D
1192
codecategories
1191
Game Dev
1167
UI Component
1161
svg
1095

Providers & pricing (5)

ProviderIn $/MOut $/MUptime
DeepInfrafp4$0.500$2.15100%
SiliconFlowfp8$0.500$2.1899.7%
AtlasCloudfp8$0.550$2.1599.8%
StreamLake$0.571$2.29100%
Novitafp8$0.700$2.50

Specifications

Context window164K
Max output33K
Knowledge cutoffMar 2025
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.350/M
ModeratedNo

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 via OpenRouter, making it 164th cheapest of 298 paid models.

How smart is R1 0528?

R1 0528 scores 27.1 on the Artificial Analysis Intelligence Index, ranking 86th of 180 benchmarked models, with a GPQA Diamond score of 81%.

How fast is R1 0528?

R1 0528 generates around 30 tokens per second with 627ms time-to-first-token (p50), the 242nd fastest tracked model.

What is R1 0528's context window?

R1 0528 supports a 164K-token context window and can output up to 33K tokens. It accepts text input.

Compare head-to-head