AI Index

DeepSeek-R1 (2025-05-28)

Language DeepSeek Partly verified Released May 28, 2025
Model ID
Context
128K
64K max output
Input price
¥4.00
per 1M tokens · Alibaba Cloud Model Studio
Output price
¥16.00
per 1M tokens
Epoch Capabilities Index
—
Not listed
LMArena Text
1,422
#83 of 149 listed

Where to run it

2 offerings · prices as listed
MeterTierPrice
Alibaba Cloud Model Studio (opens in a new tab) Official Available on this channel since Jun 4, 2025 China · CNY Context: 128KReasoning: YesTool use: YesStructured output: —Max thinking budget: 32.77KMax output: 16.38K deepseek-r1-0528
InputStandard ¥4.00 / 1M tokens
OutputStandard ¥16.00 / 1M tokens
Alibaba Cloud Model Studio (opens in a new tab) Official Available on this channel since Jun 4, 2025 China · CNY siliconflow/deepseek-r1-0528
InputStandard ¥4.00 / 1M tokens
OutputStandard ¥16.00 / 1M tokens
  1. Now priced on Alibaba Cloud Model Studio, China Input ¥4.00 · Output ¥16.00

Cited scores

From third-party leaderboards, not measured by us
  • LMArena Text 1,422

    #83 of 149 listed models · CI 1,416–1,427 · 18,059 votes

  • Epoch AI · GPQA Diamond 76.3%

    #74 of 128 listed models · ±2.4

  • LMArena Text · Chinese 1,428

    #102 of 149 listed models · CI 1,411–1,446 · 1,177 votes

  • LMArena Text · Coding 1,464

    #83 of 149 listed models · CI 1,453–1,476 · 2,681 votes

  • LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Oct 2, 2026
  • Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 3, 2026
  • changes we made