DeepSeek chat model for instruction following, coding, and analysis
DeepSeek V3.2 Thinking is offered by 3 providers on this page. Its reference price is $0.62 per 1M input tokens and $1.85 per 1M output tokens. The lowest paid channel is NanoGPT at $0.28 / $0.42 per 1M, about 2.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 128,000 to 163,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-07.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT deepseek/deepseek-v3.2:thinking | Gateway | $0.28 | $0.42 | $0.14 | — | 163,000 ⚠ | 65,536 | |
| 302.AI | Gateway | $0.29 | $0.43 | — | — | 128,000 | 128,000 | |
| Vercel AI Gateway | Cloud | $0.62 | $1.85 | — | — | 128,000 | 8,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 3 providers.
2 / 3 providers expose no reasoning control (reasoning_options: []).