Side by side pricing and context for DeepSeek R1 Distill Qwen 32B and DeepSeek R1 Distill Llama 70B (Groq). Rates are curated catalog values with last verified dates on each model page.
DeepSeek R1 Distill Qwen 32B
Distilled R1-style Qwen 32B for cheaper reasoning-flavored chat than full R1. Compare against Groq distill hosts when latency matters.
Input $0.300 / Output $0.600 per 1M
Context 128K · Approx
DeepSeek R1 Distill Llama 70B (Groq)
Distilled reasoning-style Llama on Groq when you want DeepSeek-flavored behavior with Groq latency. Compare against native DeepSeek Reasoner on cost.
Input $0.750 / Output $0.990 per 1M
Context 128K · Approx
Quick take
- DeepSeek R1 Distill Qwen 32B is cheaper on input in this catalog snapshot.
- DeepSeek R1 Distill Qwen 32B is cheaper on output in this catalog snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | DeepSeek R1 Distill Qwen 32B | DeepSeek R1 Distill Llama 70B (Groq) |
|---|---|---|
| Input / 1M | $0.300 | $0.750 |
| Output / 1M | $0.600 | $0.990 |
| Cached input / 1M | n/a | n/a |
| Context | 128K | 128K |
| Tokenizer | Approx | Approx |