Private AI

Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Nano GPT logo
NanoGPT
Search
 
 
 
 
All conversations

Create

Chat
Studio

Explore

Models
Pricing
AI Apps
Blog

Library

Gallery
Workspace
Usage & billing
API
Suggestions and bugs
Use cases

|

Terms

|

Privacy

|

Refunds
Usage & billing
Teams
Referrals
Presets
Settings
FAQPress & mediaBrand assetsBenchmarksNano RPCEarn crypto
  1. Models
  2. Text
  3. Deepseek Ai

DeepSeek R1 0528

The new (May 28th) Deepseek R1 model.

  • Reasoning

Added May 28, 2025

Model weights

Pricing

Auto routing · per 1M tokens
Input
$0.50
Output
$2.15
Cache read
$0.35
Compare provider prices

Specifications

Context window
128K
Max output
163.8K
Parameters
671B / 37B
Total / active

Benchmarks

Sourced from LMArena.

Arena Score

1421.5

Overall Rank

#132 / 421

Votes

18,151

Confidence Interval

1415.8 - 1427.2

Category Scores

Coding

#138 / 416

2,687 votes

1464.0

Math

#174 / 404

861 votes

1392.2

Longer Query

#166 / 399

3,128 votes

1407.7

Creative Writing

#134 / 419

2,408 votes

1388.5

Instruction Following

#165 / 421

4,013 votes

1390.7

Hard Prompts

#145 / 421

6,875 votes

1433.0

Additional Categories
22

Japanese

#105 / 288

621 votes

1389.2

Polish

#124 / 243

1,980 votes

1411.8

Russian

#127 / 385

1,521 votes

1412.5

Industry Medicine And Healthcare

#128 / 391

1,229 votes

1443.0

English

#130 / 421

8,150 votes

1433.7

Exclude Ties

#132 / 421

13,064 votes

1412.4

Industry Entertainment And Sports And Media

#133 / 419

3,182 votes

1388.3

Industry Software And It Services

#135 / 421

5,522 votes

1455.7

Non English

#138 / 421

9,995 votes

1403.0

Korean

#140 / 289

324 votes

1353.2

German

#142 / 320

597 votes

1392.6

Hard Prompts English

#145 / 419

3,101 votes

1441.8

Industry Writing And Literature And Language

#150 / 420

4,198 votes

1387.9

Spanish

#152 / 304

261 votes

1401.5

French

#153 / 301

236 votes

1418.1

Industry Legal And Government

#154 / 393

1,370 votes

1415.5

Industry Business And Management And Financial Operations

#156 / 414

2,847 votes

1407.1

Industry Life And Physical And Social Science

#156 / 419

3,385 votes

1426.0

Industry Mathematical

#162 / 402

918 votes

1411.0

Multi Turn

#162 / 419

2,845 votes

1404.3

Expert

#166 / 371

887 votes

1417.8

Chinese

#168 / 395

1,186 votes

1427.1

Published 2026-11-11 · Matched as DeepSeek-R1 (0528) · CC BY 4.0

LMArena Dataset

Leaderboard results

BenchmarkScoreRank on NanoGPT
Epoch AI Benchmarking Hub

Epoch AI data, CC BY 4.0 · Updated Nov 14, 2026

GPQA Diamond

76.3%

#85 of 119

OTIS Mock AIME 2024–2025

66.4%

#93 of 121

EQ-Bench

EQ-Bench data, MIT · Updated Nov 14, 2026

Creative Writing v3

1422

#65 of 96

Longform Writing

59.1

#56 of 97

UGI Leaderboard

UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026

UGI Score

43.1

#65 of 149

UGI Willingness

2.2

#101 of 149

UGI Writing

42.3

#81 of 149

Filtered and ranked to models on NanoGPT.

Providers

Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)

Auto
Auto (ZDR)
$0.50$2.15$0.35N/AN/A
Auto
Auto (Anonymized)
$0.50$2.15$0.35N/AN/A
DeepInfra
DeepInfra
FP4
US
$0.525$2.26$0.367N/AN/A
MegaNova
MegaNova
US
$0.525$2.26$0.42N/AN/A
SiliconFlow
SiliconFlow
FP8
SG
$0.525$2.29N/AN/AN/A
StreamLake
StreamLake
CN
$0.60$2.40N/AN/AN/A
Privacy:ZDR, prompts not retainedNo training on promptsRetention and training unclearMay train on prompts
Batch API
ProviderInputOutputCached input
Auto
Autodeepseek-ai/DeepSeek-R1-0528
$0.50/M$2.15/M$0.35/M

Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.

Related text models

Compare DeepSeek R1 0528 with similar models from the same provider or model family.

DeepSeek V3.1 Terminus

deepseek-ai/DeepSeek-V3.1-Terminus

DeepSeek-V3.1-Terminus. The latest update builds on V3.1's strengths while addressing key user feedback. Language consistency improvements (fewer CN/EN mix-ups, no random chars), stronger Code Agent & Search Agent performance, and more stable, reliable outputs across benchmarks. FP8.

DeepSeek V3.1

deepseek-ai/DeepSeek-V3.1

DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. This is the non-thinking version. Quantized at FP8.

DeepSeek V3.1 Terminus (Thinking)

deepseek-ai/DeepSeek-V3.1-Terminus:thinking

Thinking-enabled DeepSeek-V3.1-Terminus with improved language consistency, upgraded Code/Search Agents, and stronger stability and reliability versus V3.1. FP8.

DeepSeek V3.1 Thinking

deepseek-ai/DeepSeek-V3.1:thinking

Thinking enabled version of Deepseek V3.1. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. Quantized at FP8.

DeepSeek V3.2 Exp

deepseek-ai/deepseek-v3.2-exp

DeepSeek V3.2 Exp is an experimental V3-series model with improved long-context efficiency compared with earlier V3 releases. FP8.

DeepSeek V3.2 Exp Thinking

deepseek-ai/deepseek-v3.2-exp-thinking

DeepSeek V3.2 Exp Thinking is an experimental V3-series reasoning model with improved long-context efficiency compared with earlier V3 releases. FP8.