Llama 3.3 70B Versatile Pricing — $0.59/M input, $0.79/M output
Groq / April 2026
Input $0.59/M tokens
Output $0.79/M tokens
Context Window 128K tokens
Ultra-low latency LPU inference
Typical use cases
General-purpose inference, chat, extraction, structured output
Estimated monthly cost at scale
Assumes 50/50 input/output token split at stated daily volume.
| Daily Volume | Monthly Tokens | Estimated Monthly Cost |
|---|---|---|
| 1M tokens/day | 30M tokens | $20.70 |
| 5M tokens/day | 150M tokens | $103.50 |
| 10M tokens/day | 300M tokens | $207.00 |
vs. other Groq models
| Model | Input ($/M) | Output ($/M) | Context |
|---|---|---|---|
| Mixtral 8x7B | $0.24 | $0.24 | 32K |
| Gemma 2 9B | $0.20 | $0.20 | 8K |
| Llama 3.1 8B Instant | $0.05 | $0.08 | 128K |
| Llama 3.2 1B Preview | $0.04 | $0.04 | 128K |
| Llama 3.2 3B Preview | $0.06 | $0.06 | 128K |
| DeepSeek R1 Distill Llama 70B | $0.75 | $0.99 | 128K |
Not sure if Llama 3.3 70B Versatile is the right fit for your workload? Clawback tests cheaper alternatives against your actual prompts and tells you exactly where you're overpaying.
Test if a cheaper model matches Llama 3.3 70B Versatile quality →