NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek R1 0528

Added May 28, 2025Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

The new (May 28th) Deepseek R1 model.

  • Reasoning
  • Tools
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.50
Output
$2.15
Cache read
$0.35

Reference prices as published by the model provider. API example

Specifications

Context window
163.8K
Max output
32.8K
Average output (7 days)
1K tokens
Longer than 71% of 465 models

Side by side

DeepSeek R1 0528 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

DeepSeek R1 0528DeepSeekThis modelDeepSeek Chat 0324DeepSeekRemove
ProviderDeepSeekDeepSeek
Discovery tierOpen weightsOpen weights
AddedMay 28, 2025Jan 1, 2024
Limits
Context window163.84KBest128K
Max output32.77KBest8.19K
Average output1K tokens280 tokens
Pricing, USD per 1M tokens
Input$0.50$0.20Best
Output$2.15$0.77Best
Cache read$0.35$0.14Best
Performance
Throughput33.0 tok/sBest25.1 tok/s
Time to first token1.3 sBest2.9 s
Request success (24h)99.9%99.9%
Benchmark indexes
Intelligence Index13.1Best9.7
Coding Index—21.2
Math Index76.0Best41.0
Capabilities
ReasoningYesNo
ToolsYesYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • DeepSeek R1 0528
  • DeepSeek Chat 0324

Intelligence Index

  • DeepSeek R1 052813.1
  • DeepSeek Chat 03249.7

DeepSeek R1 0528: Better than 32% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 21.2

  • Math Index

    Composite of the math evaluations

    • DeepSeek R1 0528: 76.0Top
    • DeepSeek Chat 0324: 41.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 0.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 68 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 69 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 1.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek R1 0528: 55.7%Top
    • DeepSeek Chat 0324: 40.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek R1 0528: 15.8%Top
    • DeepSeek Chat 0324: 4.7%

  • GPQA Diamond

    Graduate-level science questions

    • DeepSeek R1 0528: 81.3%Top
    • DeepSeek Chat 0324: 65.5%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • DeepSeek R1 0528: 84.9%Top
    • DeepSeek Chat 0324: 81.9%

  • IFBench

    Following precise output instructions

    • DeepSeek R1 0528: 39.6%
    • DeepSeek Chat 0324: 41.0%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 0.0%

  • SciCode

    Scientific computing in Python

    • DeepSeek R1 0528: —
    • DeepSeek Chat 0324: 39.0%

  • LiveCodeBench

    Recent competitive programming problems

    • DeepSeek R1 0528: 77.0%Top
    • DeepSeek Chat 0324: 40.5%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • DeepSeek R1 0528: 76.0%Top
    • DeepSeek Chat 0324: 41.0%

  • AIME

    Competition mathematics

    • DeepSeek R1 0528: 89.3%Top
    • DeepSeek Chat 0324: 52.0%

  • MATH-500

    Competition math problems

    • DeepSeek R1 0528: 98.3%Top
    • DeepSeek Chat 0324: 94.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • DeepSeek R1 0528: 15.9%Top
    • DeepSeek Chat 0324: 15.2%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • DeepSeek R1 0528: 36.5%
    • DeepSeek Chat 0324: 47.1%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek R1 0528: 55.7%Top
    • DeepSeek Chat 0324: 40.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
33.0 tok/s
Faster than 23% of 250 models
Time to first token
1.3 s
Quicker than 90% of 250 models
Prompt cache hits
59.2%
About $0.41 per 1M input tokens with caching
Request success (24h)
99.9%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 62.2%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-R1-0528",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-R1-0528",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.