Model prices / DeepSeek / DeepSeek V3.1
DeepSeek V3.1Open weights
DeepSeek · released 2025-08-21
No price from the maker itself is on record for DeepSeek V3.1. The lowest of 17 providers is NanoGPT: $0.2 per 1M input tokens and $0.7 per 1M output tokens (as of 2026-11-12). Context window: 131K tokens, up to 8.2K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTLowestdeepseek-ai/ | $0.2 | $0.7 | $0.1 | Lowest | Official docs |
NNanoGPTdeepseek-ai/ | $0.2 | $0.7 | $0.1 | Official docs | |
TTokenGodeepseek/ | $0.19 | $0.71 | $0.06 | Official docs | |
MMeganovadeepseek-ai/ | $0.19 | $0.79 | — | Official docs | |
 submodeldeepseek-ai/ | $0.2 | $0.8 | — | Official docs | |
 Deep Infradeepseek-ai/ | $0.25 | $0.95 | $0.13 | Official docs | |
 Vercel AI Gatewaydeepseek/ | $0.25 | $0.95 | $0.13 | Official docs | |
 Hugging Facedeepseek-ai/ | $0.27 | $1 | — | Official docs | |
JJiekou.AIdeepseek/ | $0.27 | $1 | — | Official docs | |
 SiliconFlowdeepseek-ai/ | $0.27 | $1 | — | Official docs | |
 CoreWeavedeepseek-ai/ | $0.5 | $1.5 | $0.2 | Official docs | |
MMerge Gatewaydeepseek/ | $0.56 | $1.68 | $0.13 | Official docs |
6 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
TThinking Machinesdeepseek-ai/ | $1.695 | $4.215 | $0.339 | Official docs | |
 SambaNovaDeepSeek-V3.1 | $3 | $4.5 | — | Official docs | |
AAbacusDeprecateddeepseek/ | $0.55 | $1.66 | — | Deprecated | Official docs |
 Amazon BedrockDeprecateddeepseek. | $0.58 | $1.68 | — | Deprecated | Official docs |
 Together AIDeprecateddeepseek-ai/ | $0.6 | $1.7 | — | Deprecated | Official docs |
QQiniuDeprecateddeepseek-v3.1 | $0.57971 | $1.73913 | — | 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
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes
Description from models.dev.
Specs
- Type
- Text
- Context
- 131K
- Max output
- 8.2K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- —
- Open weights
- Yes
- Released
- 2025-08-21
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.