DeepSeek R1 Distill Qwen 32B pricing
DeepSeek R1 Distill Qwen 32B, Reasoning-tier from Cloudflare Workers AI, costs $0.497 per 1M input tokens and $4.88 per 1M output tokens.
Input$0.497per 1M tokens
Output$4.88per 1M tokens
Context window—tokens
TierReasoningCloudflare Workers AI
Price your own workload against DeepSeek R1 Distill Qwen 32B in the calculator →
Specs and pricing
| Provider | Cloudflare Workers AI |
| Tier | Reasoning |
| Context window | — |
| Max output | — |
| Input price | $0.497 / 1M tokens |
| Output price | $4.88 / 1M tokens |
| Modalities | text |
Note. Model id @cf/deepseek-ai/deepseek-r1-distill-qwen-32b. Neuron-equivalent: 45170 neurons per M input tokens, 443756 neurons per M output tokens.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.50 | $1.22 | $1.72 |
| 10,000,000 in / 2,500,000 out | $4.97 | $12.20 | $17.17 |
| 100,000,000 in / 25,000,000 out | $49.70 | $122.03 | $171.73 |
Cheaper alternatives
Same tier (Reasoning), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Trinity Large (Thinking) | Parasail | $0.22 | $0.85 | 74.8% cheaper blended |
| GPT-5.1-codex-mini | Azure OpenAI Service | $0.25 | $2.00 | 56.3% cheaper blended |
| DeepSeek-R1-Distill-Llama-70B | SambaNova | $0.70 | $1.40 | 38.9% cheaper blended |
| Kimi K2 Thinking | Novita AI | $0.60 | $2.50 | 28.7% cheaper blended |
| DeepSeek R1 0528 | Novita AI | $0.70 | $2.50 | 22.8% cheaper blended |