Distilled reasoning-style Llama on Groq when you want DeepSeek-flavored behavior with Groq latency. Compare against native DeepSeek Reasoner on cost.
Privacy first counting
TokenCALC counts tokens in your browser when an Exact encoding is available. Prompt text does not need to leave your device for local counting.
Pricing snapshot
USD per 1 million tokens. Verify against the provider source before you lock budget.
| Rate | USD |
|---|---|
| Input / 1M | $0.750 |
| Output / 1M | $0.990 |
Model details
| Detail | Value |
|---|---|
| Provider | Groq |
| Context window | 128K |
| Tokenizer | Approx |
| Last verified | 2026-08-02 |
| API model id | deepseek-r1-distill-llama-70b |