Skip to content
ModelCap

R1 0528

Current board #61Arena #117Official publisher releaseOpen weights7d #60 → #61

DeepSeek·deepseek/deepseek-r1-0528

R1 0528 is ModelCap current-board rank #61 with Index 60.5 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.

R1 0528 listed OpenRouter input price is $0.50 per 1M tokens and listed output price is $2.15 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

R1 0528 has a published context limit of 164K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

R1 0528 has 4 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

R1 0528 weight access is open weights, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
60.5#61
Measured · 62% support · score interval 55.5–65.5
Evidence as of 13 Sept 2026, 00:00 UTC
Market Gravity
32.0
Secondary market signal
Input
$0.50
per 1M tokens
Output
$2.15
per 1M tokens
Context
164K
tokens
Providers
4
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrafp4Cheapest$0.50$2.15164Kfp4100.0%
SiliconFlowfp8$0.50$2.18164Kfp899.26%
StreamLake$0.571$2.29128K99.08%
Novitafp8$0.70$2.50164Kfp8

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.50$2.15164K719 ms30.2 tok/s
novita
live
$0.70$2.50164K1128 ms29.0 tok/sstructured
featherless-ai
live

Reported evaluation leads (2)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
Idavidrein/gpqa
diamond
78.7879
Unpinned
not published
Reported
Quarantined
TIGER-Lab/MMLU-Pro
mmlu_pro
85
Unpinned
not published
Reported
Quarantined

Other versions (1)

ModelCap Index · Current board

Methodology
60.5
Measured · 2 public benchmark observations across 2 boards
Current board
#61
Public rank basis
Measured (measured)
Index support
61.9% · strong
Index interval
55.5–65.5
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
13 Sept 2026, 00:00 UTC
Identity binding
Exact catalogue product · deepseek/deepseek/deepseek-r1-0528/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata deepseek-ai/DeepSeek-R1-0528@4236a6af538feda4548eca9ab308586007567f52 (not the evaluation revision)
Index observations used
2
Qualified Index evidence point
60.5
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
60.5
Evidence status
confirmed · 77% mass
General preference
61.1
Coding
56.0
Agents & tools
Reasoning
Evidence breadth
92%
Evidence coverage
62%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
14.1
Liquidity (providers × uptime)
66.1
Open reach (HF downloads)
46.6
Surface (context / tools / modalities)
71.8
Freshness
16.0
  • · OpenRouter popularity #143
  • · 4 live providers
  • · HF 30d downloads 159501
  • · Catalogue: context 163840, reasoning, tools
  • · First seen 2025-05-28

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
84.9
strong · 94% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
96.9
Evaluation provenance
51.8

Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
32.0
OpenRouter weekly popularity
#143 of 322

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#117 of 402
Rating
1421.4
95% confidence interval
1416–1427
Votes
18K
Source published at
13 Sept 2026, 00:00 UTC
Category
overall
Identity match confidence
99%

Market Gravity breakdown

Usage55%
14.1

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
66.1

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
46.6

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
16.0

Time since first public availability, on a six-month half-life.

Specification

Context window
164K tokens
Max output
33K tokens
Inputs
Text
Outputs
Text
Tokenizer
DeepSeek
Cached input tokens
$0.35 / 1M
First seen on OpenRouter
28 May 2025
Knowledge cutoff
2025-03-31

Capabilities

  • Supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
mit
Pinned revision
4236a6af538f
Parameters
684.5B
Architecture
DeepseekV3ForCausalLM
Model type
deepseek_v3
Hugging Face downloads (30d)
160K
Downloads (all time)
16.9M
Likes
2K
Repository updated
29 May 2025, 11:37 UTC

Compare R1 0528 with

Pick any model

Benchmark leaderboards featuring R1 0528

All leaderboards
Public benchmark boards on which R1 0528 has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)14641453–1475#121 of 397Default13 Sept 2026

Alternatives to R1 0528, by the numbers

Ranked neighbours

Models within 3 places of #61 on the ModelCap Index.

Cheaper at a similar or higher Index

Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).

Other ranked DeepSeek models

The same publisher's other current models with a public Index position.

R1 0528: common questions

How does R1 0528 rank among AI models?

R1 0528 holds ModelCap Index position #61 of 248 ranked language models as of 22 September 2026, with an Index score of 60.5 (interval 55.5–65.5); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does R1 0528 cost per 1M tokens?

R1 0528 is listed at $0.50 per 1M input tokens and $2.15 per 1M output tokens as of 22 September 2026 across 4 providers. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $2.08 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of R1 0528?

R1 0528 has a published context window of 164K tokens (163,840) and a maximum output of 33K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is R1 0528 open-weight?

Open weights (mit). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is deepseek-ai/DeepSeek-R1-0528 on Hugging Face.

Which API providers serve R1 0528?

4 providers serve R1 0528 through OpenRouter as of 22 September 2026: DeepInfra, SiliconFlow, StreamLake and Novita. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has R1 0528 been evaluated on?

R1 0528 has published results on 1 public board tracked by ModelCap as of 22 September 2026: Arena coding 1464 (#121 of 397). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does R1 0528 compare with DeepSeek V3.2?

R1 0528 ranks #61 (Index 60.5) and DeepSeek V3.2 ranks #60 (Index 60.8) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was R1 0528 released?

R1 0528 first appeared in the catalogue on 28 May 2025, with a published knowledge cutoff of 2025-03-31. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.