R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving
DeepSeek-R1-Distill-Qwen-32B is offered by 3 providers on this page. Its reference price is $0.497 per 1M input tokens and $4.88 per 1M output tokens. The lowest paid channel is NovitaAI at $0.30 / $0.30 per 1M, about 1.7× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 8.4 on the Intelligence Index. Against its lowest blended price of $0.30 per 1M, that is roughly 28 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 80,000 tokens at the reference host, but hosts report different limits, from 32,768 to 80,000, so the usable window depends on the provider you pick. It supports reasoning. The weights are open, so it can also be self-hosted or served through a gateway of your choice. 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.
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 |
|---|---|---|---|---|---|---|---|---|
| NovitaAI | Gateway | $0.30 | $0.30 | — | — | 64,000 ⚠ | 32,000 | |
| Alibaba (China) | First-party | $0.29 | $0.86 | — | — | 32,768 ⚠ | 16,384 | |
| Cloudflare Workers AI | Cloud | $0.50 | $4.88 | — | — | 80,000 | 80,000 |
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 / 3 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.