DeepSeek model product
DeepSeek-R1
DeepSeek-R1 is a reasoning model for complex reasoning, mathematical problem-solving, and code generation through a thinking mode approach.
Updated Oct 23, 2026. Default version: DeepSeek-R1-0528
LLMBoard Score41.6DeepSeek-R1-0528
Coverage80%16 benchmark families
Context window163.8KTokens
Official input priceN/AOfficial price unavailable
DeepSeek-R1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-R1 Benchmark Results
Benchmark scores for DeepSeek-R1-0528.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSimpleQA | Score92.30% | Rank04 | Participants47 | Percentile93.48% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score71.60% | Rank06 | Participants22 | Percentile76.19% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score91.40% | Rank07 | Participants54 | Percentile88.68% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score93.40% | Rank10 | Participants50 | Percentile81.63% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score35.70% | Rank15 | Participants15 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score64.33% | Rank16 | Participants20 | Percentile21.05% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score73.30% | Rank20 | Participants76 | Percentile74.67% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score85.00% | Rank21 | Participants142 | Percentile85.82% | EvidenceC | Evaluated |
| BenchmarkHMMT 2025 | Score79.40% | Rank25 | Participants33 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score5.70% | Rank25 | Participants25 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score30.50% | Rank50 | Participants50 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score87.50% | Rank58 | Participants122 | Percentile52.89% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score8.90% | Rank70 | Participants70 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score17.70% | Rank78 | Participants109 | Percentile28.70% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,427.82 rating | Rank78 | Participants218 | Percentile64.52% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score81.00% | Rank96 | Participants256 | Percentile62.75% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,421.55 rating | Rank98 | Participants218 | Percentile55.30% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score44.60% | Rank107 | Participants120 | Percentile10.92% | EvidenceC | Evaluated |
DeepSeek-R1 Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext | Categorycreative writing | Rank61 | Rating / score1,405.34 | Votes2,408 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank65 | Rating / score1,445.36 | Votes1,228 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank69 | Rating / score1,428.15 | Votes1,980 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank70 | Rating / score1,391.01 | Votes620 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank71 | Rating / score1,400.34 | Votes3,182 | ObservationsN/A | Result date |
| Arenatext | Categoryrussian | Rank71 | Rating / score1,423.01 | Votes1,524 | ObservationsN/A | Result date |
| Arenatext | Categoryexclude ties | Rank76 | Rating / score1,420.00 | Votes13,076 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank76 | Rating / score1,389.27 | Votes620 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank78 | Rating / score1,427.82 | Votes18,165 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank79 | Rating / score1,437.21 | Votes8,162 | ObservationsN/A | Result date |
| Arenatext | Categorynon english | Rank81 | Rating / score1,411.93 | Votes9,997 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry writing and literature and language | Rank85 | Rating / score1,401.83 | Votes4,199 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank90 | Rating / score1,443.17 | Votes1,228 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank91 | Rating / score1,411.82 | Votes1,980 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry life and physical and social science | Rank92 | Rating / score1,430.25 | Votes3,387 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank93 | Rating / score1,413.19 | Votes1,524 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank95 | Rating / score1,404.26 | Votes597 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank96 | Rating / score1,359.71 | Votes323 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry software and it services | Rank97 | Rating / score1,434.92 | Votes5,531 | ObservationsN/A | Result date |
| Arenatext style control | Categoryexclude ties | Rank97 | Rating / score1,412.33 | Votes13,076 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank97 | Rating / score1,388.33 | Votes3,182 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank98 | Rating / score1,388.85 | Votes2,408 | ObservationsN/A | Result date |
| Arenatext style control | Categoryenglish | Rank98 | Rating / score1,433.62 | Votes8,162 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank98 | Rating / score1,421.55 | Votes18,165 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank99 | Rating / score1,464.05 | Votes2,690 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank99 | Rating / score1,455.86 | Votes5,531 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank99 | Rating / score1,403.18 | Votes9,997 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank101 | Rating / score1,411.43 | Votes261 | ObservationsN/A | Result date |
| Arenatext | Categoryhard prompts | Rank102 | Rating / score1,415.50 | Votes6,879 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry legal and government | Rank102 | Rating / score1,418.89 | Votes1,369 | ObservationsN/A | Result date |
DeepSeek-R1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.20 input, $0.80 output per 1M via submodel
- Tracked offerings
- 14
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| Providersubmodel | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.20 | Output / 1M$0.80 | Context75K | Updated |
| ProviderMeganova | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| ProviderNanoGPT | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| ProviderDeep Infra | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| ProviderOpenRouter | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| ProviderKilo Gateway | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context163.8K | Updated |
| ProviderAlibaba (China) | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.574 | Output / 1M$2.29 | Context131.1K | Updated |
| ProviderQiniu | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.5797 | Output / 1M$2.32 | Context128K | Updated |
| ProviderTensorX | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.66 | Output / 1M$2.6 | Context164K | Updated |
| ProviderMelious | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.6955 | Output / 1M$2.78 | Context164K | Updated |
| ProviderJiekou.AI | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderNovita AI | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderMerge Gateway | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$1.35 | Output / 1M$5.4 | Context65.5K | Updated |
| ProviderHugging Face | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$3 | Output / 1M$5 | Context163.8K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
DeepSeek-R1 Runtime Performance
Provider-specific output speed and catalog latency for DeepSeek-R1-0528. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepSeek | Output Speed9.00 tok/s | Catalog Latency0.30 s | Max Input131.1K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
DeepSeek-R1 Specifications
Technical details for the model's default version.
- Version
- DeepSeek-R1-0528
- Released
- May 28, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 671B
- Context window
- 163.8K
- Max output
- 163.8K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
DeepSeek-R1 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionDeepSeek-R1-0528 | Released | LLMBoard41.63 | Parameters671B | Context163.8K | Max output163.8K | Open weightsYes | LicenseMIT |
| VersionDeepSeek R1 Zero | Released | LLMBoardN/A | Parameters671B | ContextN/A | Max outputN/A | Open weightsYes | LicenseMIT |
| VersionDeepSeek-R1 | Released | LLMBoardN/A | Parameters671B | Context131.1K | Max output131.1K | Open weightsYes | LicenseMIT |
Models similar to DeepSeek-R1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-V3.2
DeepSeek
DE
DeepSeek-V3
DeepSeek
DE
DeepSeek-R1-Distill-Qwen
DeepSeek
DE
DeepSeek-V2.5
DeepSeek
DE
DeepSeek-V4-Flash
DeepSeek
What is DeepSeek-R1?
Key information about DeepSeek-R1 and its available data.
DeepSeek-R1 is DeepSeek's reasoning model, with DeepSeek-R1-0528 identified as its May 28, 2025 version. 1.
Data as of 2026-10-22.
FAQ
Common questions about DeepSeek-R1.
When was DeepSeek-R1 released?
DeepSeek-R1's default version was released on May 28, 2025.
How much does DeepSeek-R1 cost?
No official standard PAYG price is currently available for DeepSeek-R1. The lowest tracked third-party offer starts at $0.20 input and $0.80 output via submodel.
Who created DeepSeek-R1?
DeepSeek-R1 was created by DeepSeek.
What is the context window for DeepSeek-R1?
The default version has a 163.8K token context window.
Is DeepSeek-R1 open weight?
Yes. The default version is marked as open weight under MIT.
How many API providers offer DeepSeek-R1?
14 provider offerings are linked to the default version.