← Hosted open-model inference
Groq
Llama 3.3 70B (Groq)
Extremely fast LPU-based inference. Sample entry.
USD per 1M output tokens
$0.79
- input
- $0.59
- output
- $0.79
Unverified sample
#5 cheapest of 15 in Hosted open-model inference
Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
Model
llama
Which open-weight model family is served.
Output speed
300 tok/s
How fast text is generated.
Precision
fp8
Numerical precision served. bf16 is the reference quality.
Context window
128K tokens
Context length offered by this host.
Price history
Only one price recorded so far. The chart appears once the price changes.