Intelligence
20 scoreDeepSeek · Flagships Analysis
DeepSeek R1 0528
Intelligence, Performance & Price Analysis
Canonical slug: deepseek-r1 · Canonical model registry at build time
Input Price
$1.35 / 1M tokensOutput Price
$4.20 / 1M tokensExecutive Assessment
Routing Verdict & Tradeoffs
Ethen Routing Verdict
Strong general-purpose model
DeepSeek R1 0528 (May '25) scores 20 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 25). DeepSeek R1 0528 (May '25) costs $1.35 per 1M input tokens (at the higher end, median: $0.59) and $4.20 per 1M output tokens (at the higher end, median: $2.20), based on the median across providers serving the model.
Suitable for most production tasks, but high-volume or repetitive work should still be compared against cheaper routes.
Task Fit Assessment
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | optimal | Intelligence score 20 supports capable reasoning, but very hard tasks may benefit from higher-tier models. |
| Cost-sensitive pipelines | viable | Output pricing at $4.20 is premium. Route high-volume simple tasks to cheaper alternatives. |
Cost Pressure Analysis
High
Pricing is premium — input $1.35, output $4.20. This model is expensive for high-volume or output-heavy workloads.
Technical Specifications
Architecture and Limits
| Specification | Value | Validation Authority |
|---|---|---|
| Model type | Open weights | inferred |
| Reasoning | Yes | faq |
| Input modalities | DeepSeek R1 0528 (May '25) supports text input. | faq |
| Output modalities | DeepSeek R1 0528 (May '25) supports text output. | faq |
| Context window | 130k tokens | faq |
| Open weights / source | Yes, DeepSeek R1 0528 (May '25) is open weights. The model weights are publicly available and can be downloaded for self-hosting. | faq |
| Parameters | DeepSeek R1 0528 (May '25) has 685 billion parameters (37 billion active). | faq |
| Active parameters | DeepSeek R1 0528 (May '25) is a Mixture of Experts (MoE) model with 685 billion total parameters, but only 37 billion active parameters are used during inference. | faq |
| License | DeepSeek R1 0528 (May '25) is released under the MIT license. This license allows commercial use. | faq |
| API availability | Yes, DeepSeek R1 0528 (May '25) is available via API through 6 providers. | faq |
Evidence charts
Profile visualizations
Charts are the same canonical evidence cards previously published for this slug, contained inside the D18D page grammar.
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Openness Index: Score
Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Bars intentionally show many models at once so the page feels like a benchmark report rather than a dashboard.
Model Size: Total and Active Parameters
Comparison between total model parameters and parameters active during inference · Evaluation results measured independently by Artificial Analysis
Retrieved 2026-07-08
Chart source and provenance are listed in Methodology & sources below.
- Source:
- Published benchmark dataset
- Retrieval date:
- 2026-07-08
- Methodology:
- Independent test run by Artificial Analysis on dedicated hardware.
Larger models generally perform better but cost more to serve. Active parameter count matters for inference efficiency.
Methodology
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for DeepSeek R1 0528.
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Frequently Asked Questions
Model FAQs & Technical Disclosures
DeepSeek R1 0528 (May '25) was released on May 28, 2025.
DeepSeek R1 0528 (May '25) was created by DeepSeek.
DeepSeek R1 0528 (May '25) scores 20 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 25).
DeepSeek R1 0528 (May '25) costs $1.35 per 1M input tokens (at the higher end, median: $0.59) and $4.20 per 1M output tokens (at the higher end, median: $2.20), based on the median across providers serving the model.
DeepSeek R1 0528 (May '25) costs $1.35 per 1M input tokens and $4.20 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.64 per 1M tokens. Pricing may vary by provider.
Yes, DeepSeek R1 0528 (May '25) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
DeepSeek R1 0528 (May '25) supports text input.
DeepSeek R1 0528 (May '25) supports text output.
No, DeepSeek R1 0528 (May '25) does not support image input. It can only process text.
No, DeepSeek R1 0528 (May '25) is not multimodal. It only supports text input.
DeepSeek R1 0528 (May '25) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, DeepSeek R1 0528 (May '25) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
DeepSeek R1 0528 (May '25) has 685 billion parameters (37 billion active).
DeepSeek R1 0528 (May '25) is a Mixture of Experts (MoE) model with 685 billion total parameters, but only 37 billion active parameters are used during inference.
DeepSeek R1 0528 (May '25) is released under the MIT license. This license allows commercial use.
DeepSeek R1 0528 (May '25) achieves a score of 20 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, DeepSeek R1 0528 (May '25) is available via API through 6 providers.
DeepSeek R1 0528 (May '25) is available through 6 API providers.