Model prices / DeepSeek / DeepSeek R1 0528
DeepSeek R1 0528Open weights
DeepSeek · released 2025-05-28
No price from the maker itself is on record for DeepSeek R1 0528. The lowest of 16 providers is submodel: $0.2 per 1M input tokens and $0.8 per 1M output tokens (as of 2026-11-12). Context window: 164K tokens, up to 32.8K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 submodelLowestdeepseek-ai/ | $0.2 | $0.8 | — | Lowest | Official docs |
 Deep Infradeepseek-ai/ | $0.5 | $2.15 | $0.35 | Official docs | |
EEden AIdeepinfra/ | $0.5 | $2.15 | $0.35 | Official docs | |
KKilo Gatewaydeepseek/ | $0.5 | $2.15 | $0.35 | Official docs | |
MMeganovadeepseek-ai/ | $0.5 | $2.15 | $0.4 | Official docs | |
NNanoGPTdeepseek-ai/ | $0.5 | $2.15 | $0.35 | Official docs | |
 OpenRouterdeepseek/ | $0.5 | $2.15 | $0.35 | Official docs | |
 SiliconFlowdeepseek-ai/ | $0.5 | $2.18 | — | Official docs | |
 IO.NETdeepseek-ai/ | $0.523667 | $2.205333 | $0.261834 | Official docs | |
| SiliconFlow (China)Pro/ | $0.59779 | $2.39116 | $0.059779 | Official docs | |
| SiliconFlow (China)deepseek-ai/ | $0.59779 | $2.39116 | $0.059779 | Official docs | |
JJiekou.AIdeepseek/ | $0.7 | $2.5 | $0.35 | Official docs |
6 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 Novita AIdeepseek/ | $0.7 | $2.5 | $0.35 | Official docs | |
EEden AItensorx/ | $0.66 | $2.6 | $0.165 | Official docs | |
MMerge Gatewaydeepseek/ | $1.35 | $5.4 | $0.945 | Official docs | |
 Hugging Facedeepseek-ai/ | $3 | $5 | — | Official docs | |
QQiniuDeprecateddeepseek-r1-0528 | $0.57971 | $2.318841 | — | Deprecated | Official docs |
TTensorXDeprecateddeepseek/ | $0.66 | $2.6 | $0.165 | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
Description from models.dev.
Specs
- Type
- Text
- Context
- 164K
- Max output
- 32.8K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2024-07
- Open weights
- Yes
- Released
- 2025-05-28
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.