DeepSeek chat model for instruction following, coding, and analysis
DeepSeek-V3.2-Speciale is offered by 2 providers on this page. Its reference price is $0.58 per 1M input tokens and $1.68 per 1M output tokens.
Artificial Analysis rates it 14.5 on the Intelligence Index. Against its lowest blended price of $0.855 per 1M, that is roughly 17 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 128,000 tokens, with an output limit of 128,000 tokens. It supports reasoning. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Its training knowledge cuts off at 2024-07.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Azure | Cloud | $0.58 | $1.68 | — | — | 128,000 | 128,000 | |
| Azure Cognitive Services | Cloud | $0.58 | $1.68 | — | — | 128,000 | 128,000 |
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.
2 / 2 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.