# DeepSeek V3.2 Exp Thinking API prices

DeepSeek V3.2 Exp Thinking (deepseek-thinking) — 164k context, 66k max output.
1 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| NanoGPT | $0.28 | $0.42 | $0.14 | 164k |

## Summary

- Cheapest input: $0.28 per 1M tokens (NanoGPT)
- Cheapest output: $0.42 per 1M tokens (NanoGPT)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2024-01-01
- Inputs: text

## FAQ

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

As of Oct 4, 2026, NanoGPT has the lowest DeepSeek V3.2 Exp Thinking output price at $0.42 per 1M tokens, and NanoGPT has the lowest input price at $0.28 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 Exp Thinking?

2 providers list DeepSeek V3.2 Exp Thinking on Sovyron; 1 of them sell it at a metered per-token price.

### Is DeepSeek V3.2 Exp Thinking free?

No provider in the Sovyron catalog lists a free tier for DeepSeek V3.2 Exp Thinking.

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

DeepSeek V3.2 Exp Thinking supports a 164k-token context window and up to 66k output tokens.

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