DeepSeek V3.1
As of Oct 4, 2026, the cheapest DeepSeek V3.1 API price is $0.19 per 1M input tokens (TokenGo) and $0.7 per 1M output tokens (NanoGPT). DeepSeek V3.1 is offered by 18 providers in the deepseek family, open weights, reasoning enabled.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| TokenGoopen | Cheapest$0.19 | $0.71 | $0.06 | — | 131k | — |
| NanoGPTopen | $0.2 | Cheapest$0.7 | $0.1 | — | 128k | — |
| submodel | $0.2 | $0.8 | — | — | 75k | — |
| Deep Infraopen | $0.25 | $0.95 | $0.13 | — | 164k | — |
| Kilo Gateway | $0.25 | $0.95 | $0.13 | — | 164k | 5d agoout −5% |
| OpenRouteropen | $0.25 | $0.95 | $0.13 | — | 164k | — |
| Vercel AI Gatewayopen | $0.25 | $0.95 | $0.13 | — | 164k | — |
| Hugging Faceopen | $0.27 | $1 | — | — | 131k | — |
| Jiekou.AIopen | $0.27 | $1 | — | — | 164k | — |
| Meganovaopen | $0.27 | $1 | — | — | 164k | — |
| NovitaAIopen | $0.27 | $1 | $0.135 | — | 131k | — |
| Merge Gatewayopen | $0.5 | $1.5 | — | — | 164k | — |
| CoreWeaveopen | $0.55 | $1.65 | $0.55 | — | 161k | — |
| Abacusopen | $0.55 | $1.66 | — | — | 128k | — |
| Pioneeropen | $0.56 | $1.68 | $0.56 | $0.56 | 164k | — |
| Amazon Bedrockopen | $0.58 | $1.68 | — | — | 164k | — |
| Alibaba (China) | $0.574 | $1.721 | — | — | 131k | — |
DeepSeek V3.1 pricing FAQ
What is the cheapest DeepSeek V3.1 API?
As of Oct 4, 2026, NanoGPT has the lowest DeepSeek V3.1 output price at $0.7 per 1M tokens, and TokenGo has the lowest input price at $0.19 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer DeepSeek V3.1?
18 providers list DeepSeek V3.1 on Sovyron; 17 of them sell it at a metered per-token price.
Is DeepSeek V3.1 free?
No provider in the Sovyron catalog lists a free tier for DeepSeek V3.1.
What is the context window of DeepSeek V3.1?
DeepSeek V3.1 supports a 164k-token context window and up to 164k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.
Estimated
—