# DeepSeek V3.2 API prices

DeepSeek V3.2 (deepseek) — 164k context, 164k max output.
31 metered per-token offers from 32 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| CrofAI | $0.18 | $0.35 | $0.04 | 164k |
| TokenGo | $0.2174 | $0.326 | $0.06 | 128k |
| Deep Infra | $0.26 | $0.38 | $0.13 | 164k |
| DevPass (LLM Gateway) | $0.26 | $0.38 | $0.13 | 164k |
| LLM Gateway | $0.26 | $0.38 | $0.13 | 160k |
| Meganova | $0.26 | $0.38 | — | 164k |
| LLM Gateway | $0.269 | $0.4 | $0.1345 | 164k |
| NovitaAI | $0.269 | $0.4 | $0.1345 | 164k |
| Abacus | $0.27 | $0.4 | — | 128k |
| Poe | $0.27 | $0.4 | $0.13 | 128k |
| Helicone | $0.27 | $0.41 | — | 164k |
| Hugging Face | $0.28 | $0.4 | — | 164k |
| Merge Gateway | $0.28 | $0.4 | $0.13 | 128k |
| Kilo Gateway | $0.28 | $0.42 | $0.028 | 131k |
| NanoGPT | $0.28 | $0.42 | $0.14 | 163k |
| OpenRouter | $0.28 | $0.42 | $0.028 | 164k |
| Vivgrid | $0.28 | $0.42 | — | 128k |
| ZenMux | $0.28 | $0.43 | — | 128k |
| 302.AI | $0.29 | $0.43 | — | 128k |
| Ofox | $0.29 | $0.43 | $0.06 | 128k |
| Cortecs | $0.296 | $0.495 | $0.075 | 164k |
| TensorX | $0.3 | $0.5 | $0.075 | 164k |
| Venice AI | $0.33 | $0.48 | $0.16 | 160k |
| Melious | $0.3478 | $0.5796 | $0.0927 | 164k |
| Friendli | $0.5 | $1.5 | $0.25 | 164k |
| LLM Gateway | $0.56 | $1.68 | $0.056 | 164k |
| Azure | $0.58 | $1.68 | — | 128k |
| Azure Cognitive Services | $0.58 | $1.68 | — | 128k |
| EmpirioLabs AI | $0.57 | $1.71 | $0.57 | 128k |
| Amazon Bedrock | $0.62 | $1.85 | — | 164k |
| Vercel AI Gateway | $0.62 | $1.85 | — | 128k |

## Summary

- Cheapest input: $0.18 per 1M tokens (CrofAI)
- Cheapest output: $0.326 per 1M tokens (TokenGo)
- First-party: not listed separately
- Free offers: Alibaba Token Plan, Alibaba Token Plan (China)
- Subscription plans (not per-token): Alibaba Token Plan, Alibaba Token Plan (China)
- Released: 2025-12-01
- Inputs: image, pdf, text

## FAQ

### What is the cheapest DeepSeek V3.2 API?

As of Oct 4, 2026, TokenGo has the lowest DeepSeek V3.2 output price at $0.326 per 1M tokens, and CrofAI has the lowest input price at $0.18 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?

32 providers list DeepSeek V3.2 on Sovyron; 31 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.

### Is DeepSeek V3.2 included in a subscription plan?

Yes. 3 flat-rate plan(s) include it; the cheapest is Qwen (Alibaba Cloud) Token Plan Lite at $8/month.

### What is the context window of DeepSeek V3.2?

DeepSeek V3.2 supports a 164k-token context window and up to 164k output tokens.

HTML page: https://sovyron.com/models/deepseek-v3-2/
Full dataset: https://sovyron.com/data/catalog.json