DeepSeek: R1 0528
deepseek/deepseek-r1-0528
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
Prompt $/1M
$0.500
Completion $/1M
$2.150
Context
163,840 tok
Best provider
134 tok/s · Nebius
Specs
- Model id
- deepseek/deepseek-r1-0528
- Display name
- DeepSeek: R1 0528
- Modality
- text->text
- Tokenizer
- DeepSeek
- Instruct type
- deepseek-r1
- Context length
- 163,840
- Max completion
- 32,768
- Prompt $/1M
- $0.500
- Completion $/1M
- $2.150
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Nebiusfastest | 134 |
| Togetherfastest | 108 |
| SambaNova | 62 |
| StreamLakefastest | 32 |
| AtlasCloud | 26 |
| Chutes | 25 |
| Novita | 24 |
| DeepInfra | 23 |
| SiliconFlow | 18 |