← Hosted open-model inference
Novita AI
Llama 3.3 70B (Novita)
Low-cost hosted Llama 3.3 70B; batch inference is 50% off.
USD per 1M output tokens
$0.40
- input
- $0.135
- output
- $0.40
Verified Oct 6, 2026
#2 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
—
How fast text is generated.
Precision
—
Numerical precision served. bf16 is the reference quality.
Context window
—
Context length offered by this host.
Price history
Only one price recorded so far. The chart appears once the price changes.