DeepSeek V3.2
As of Nov 22, 2026, the cheapest DeepSeek V3.2 API price is $0.2174 per 1M input tokens (TokenGo) and $0.326 per 1M output tokens (TokenGo). DeepSeek V3.2 is offered by 23 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. Seeing a wide range? Why the same LLM costs different amounts.
| TokenGoopendeepseek/deepseek-v3.2 | Cheapest$0.2174 | Cheapest$0.326 | $0.06 | — | 128k | — |
| Deep Infraopendeepseek-ai/DeepSeek-V3.2 | $0.26 | $0.38 | $0.13 | — | 164k | — |
| Kilo Gatewayopendeepseek/deepseek-v3.2 | $0.26 | $0.38 | $0.13 | — | 164k | 22d agoout −9.5% |
| DevPass (LLM Gateway)opendeepseek-v3.2 | $0.26 | $0.38 | $0.13 | — | 164k | — |
| LLM Gatewayopendeepinfra/deepseek-v3.2 | $0.26 | $0.38 | $0.13 | — | 160k | — |
| Meganovaopendeepseek-ai/DeepSeek-V3.2 | $0.26 | $0.38 | $0.13 | — | 164k | — |
| NanoGPTopendeepseek/deepseek-v3.2 | $0.26 | $0.38 | $0.13 | — | 163k | 8d agoout −9.1% |
| OpenRouteropendeepseek/deepseek-v3.2 | $0.26 | $0.38 | $0.13 | — | 164k | 22d agoout −9.5% |
| Poeopennovita/deepseek-v3.2 | $0.2626 | $0.3838 | $0.1313 | — | 128k | 31d ago |
| Runcrateopendeepseek-ai/DeepSeek-V3.2 | $0.273 | $0.399 | $0.1365 | — | 164k | — |
| Heliconeopendeepseek-v3.2 | $0.27 | $0.41 | — | — | 164k | — |
| Hugging Faceopendeepseek-ai/DeepSeek-V3.2 | $0.28 | $0.4 | — | — | 164k | — |
| Merge Gatewayopendeepseek/deepseek-v3.2 | $0.28 | $0.4 | $0.13 | — | 128k | 52d ago |
| $0.29 | $0.43 | — | — | 128k | — | |
| Ofoxopendeepseek/deepseek-v3.2 | $0.29 | $0.43 | $0.06 | — | 128k | — |
| ZenMuxopendeepseek/deepseek-v3.2 | $0.293 | $0.4395 | $0.0293 | — | 128k | 31d ago |
| Cortecsopendeepseek-v3.2 | $0.5 | $1.499 | $0.15 | — | 164k | 48d ago |
| Azureopendeepseek-v3.2 | $0.58 | $1.68 | — | — | 128k | — |
| Azure Cognitive Servicesopendeepseek-v3.2 | $0.58 | $1.68 | — | — | 128k | — |
| Amazon Bedrockopendeepseek.v3.2 | $0.62 | $1.85 | — | — | 164k | — |
| Vercel AI Gatewayopendeepseek/deepseek-v3.2 | $0.62 | $1.85 | — | — | 128k | — |
| Phalaopendeepseek/deepseek-v3.2 | $1 | $1 | $0.5 | — | 164k | — |
| NEAR AI Cloudopendeepseek/deepseek-v3.2 | $1.1 | $1.1 | $0.55 | — | 128k | — |
DeepSeek V3.2 price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 7 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| NanoGPT | $0.286 → $0.26 | $0.418 → $0.38 | −9.1% | |
| NanoGPT | $0.2088 → $0.286 | $0.3096 → $0.418 | +35% | |
| Kilo Gateway | $0.28 → $0.26 | $0.42 → $0.38 | −9.5% | |
| OpenRouter | $0.28 → $0.26 | $0.42 → $0.38 | −9.5% | |
| Poe | $0.27 → $0.2626 | $0.4 → $0.3838 | −4.1% | |
| ZenMux | $0.28 → $0.293 | $0.43 → $0.4395 | +2.2% | |
| Kilo Gateway | $0.259 → $0.28 | $0.8 → $0.42 | −47.5% | |
| OpenRouter | $0.259 → $0.28 | $0.8 → $0.42 | −47.5% | |
| NanoGPT | $0.28 → $0.2088 | $0.42 → $0.3096 | −26.3% | |
| Kilo Gateway | $0.259 | $0.42 → $0.8 | +90.5% | |
| OpenRouter | $0.259 | $0.42 → $0.8 | +90.5% | |
| Kilo Gateway | $0.28 → $0.259 | $0.42 | −7.5% | |
| OpenRouter | $0.28 → $0.259 | $0.42 | −7.5% | |
| Cortecs | $0.296 → $0.5 | $0.495 → $1.499 | +202.8% | |
| Merge Gateway | $0.28 | $0.45 → $0.4 | −11.1% | |
| Kilo Gateway | $0.269 → $0.28 | $0.4 → $0.42 | +5% | |
| OpenRouter | $0.269 → $0.28 | $0.4 → $0.42 | +5% |
DeepSeek V3.2 pricing FAQ
What is the cheapest DeepSeek V3.2 API?
As of Nov 22, 2026, TokenGo has the lowest DeepSeek V3.2 output price at $0.326 per 1M tokens, and TokenGo has the lowest input price at $0.2174 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer DeepSeek V3.2?
23 providers list DeepSeek V3.2 on Sovyron; 23 of them sell it at a metered per-token price.
Is DeepSeek V3.2 free?
No provider in the Sovyron catalog lists a free tier for DeepSeek V3.2.
What is the context window of DeepSeek V3.2?
DeepSeek V3.2 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. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—