DeepSeek model product
DeepSeek-R1
DeepSeek-R1 is a reasoning-focused language model from DeepSeek that features advanced thinking capabilities.
Updated Aug 17, 2026. Default version: DeepSeek-R1-0528
LLMBoard Score43.5DeepSeek-R1-0528
Coverage80%16 benchmark families
Context window131.1KTokens
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 | Score92.3% | Rank04 | Participants47 | Percentile93.5% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score71.6% | Rank06 | Participants22 | Percentile76.2% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score91.4% | Rank07 | Participants53 | Percentile88.5% | EvidenceC | Evaluated |
| BenchmarkMMLU-Redux | Score93.4% | Rank10 | Participants48 | Percentile80.8% | EvidenceC | Evaluated |
| BenchmarkBrowseComp-zh | Score35.7% | Rank13 | Participants13 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkCodeForces | Score64.3% | Rank15 | Participants17 | Percentile12.5% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score73.3% | Rank19 | Participants75 | Percentile75.7% | EvidenceC | Evaluated |
| BenchmarkMMLU-Pro | Score85.0% | Rank20 | Participants134 | Percentile85.7% | EvidenceC | Evaluated |
| BenchmarkHMMT 2025 | Score79.4% | Rank25 | Participants33 | Percentile25.0% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench | Score5.7% | Rank25 | Participants25 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score30.5% | Rank38 | Participants38 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score87.5% | Rank55 | Participants115 | Percentile52.6% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score8.9% | Rank62 | Participants62 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score17.7% | Rank69 | Participants99 | Percentile30.6% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score81.0% | Rank85 | Participants239 | Percentile64.7% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score44.6% | Rank98 | Participants111 | Percentile11.8% | 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 | Categoryoverall | Rank81 | Rating / score1427.9 | Votes18,496 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank108 | Rating / score1421.9 | Votes18,496 | 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 $0.40 input, $1.7 output per 1M via NanoGPT
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNanoGPT | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.40 | Output / 1M$1.7 | Context128K | Updated |
| ProviderMeganova | 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 |
| Providersubmodel | Provider model IDdeepseek-ai/DeepSeek-R1-0528 | Regionglobal | Input / 1M$0.50 | Output / 1M$2.15 | Context75K | Updated |
| ProviderAlibaba (China) | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.574 | Output / 1M$2.29 | Context131.1K | Updated |
| ProviderCortecs | Provider model IDdeepseek-r1-0528 | Regionglobal | Input / 1M$0.652 | Output / 1M$2.57 | Context164K | Updated |
| ProviderTensorX | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.66 | Output / 1M$2.6 | Context164K | Updated |
| ProviderJiekou.AI | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderNovitaAI | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | Updated |
| ProviderKilo Gateway | Provider model IDdeepseek/deepseek-r1-0528 | Regionglobal | Input / 1M$0.70 | Output / 1M$2.5 | Context163.8K | 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 |
|---|
| ProviderDeepInfra | Output Speed45.04 tok/s | Catalog Latency0.61 s | Max Input131.1K | Max Output131.1K | Updated |
| ProviderNovita | Output Speed37.96 tok/s | Catalog Latency1.18 s | Max Input131.1K | Max Output32.8K | Updated |
| ProviderDeepSeek | Output Speed9 tok/s | Catalog Latency0.3 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
- 131.1K
- Max output
- 131.1K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- 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 | LLMBoard43.5 | Parameters671B | Context131.1K | Max output131.1K | Open weightsNo | LicenseMIT |
| VersionDeepSeek-R1 | Released | LLMBoardN/A | Parameters671B | Context128K | Max output32.8K | Open weightsYes | LicenseMIT |
| VersionDeepSeek R1 Zero | Released | LLMBoardN/A | Parameters671B | ContextN/A | Max outputN/A | Open weightsNo | LicenseMIT |
DeepSeek-R1 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
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-R1-Distill-Llama
DeepSeek
What is DeepSeek-R1?
Key information about DeepSeek-R1 and its available data.
DeepSeek-R1 is a reasoning-focused language model from DeepSeek that features advanced thinking capabilities. It serves as the foundation for DeepSeek's reasoning model family and pioneered their thinking mode approach for complex problem-solving tasks.
Data as of 2026-08-17.
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 $0.40 input and $1.7 output via NanoGPT.
Who created DeepSeek-R1?
DeepSeek-R1 was created by DeepSeek.
What is the context window for DeepSeek-R1?
The default version has a 131.1K token context window.
Is DeepSeek-R1 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer DeepSeek-R1?
12 provider offerings are linked to the default version.
What models should I compare DeepSeek-R1 with?
Nearby ranked alternatives include Nemotron 3 Super, GPT-5-Codex, Sarvam 105B.