# Novita AI

Canonical: https://inetgeek.com/llm-apis/novita/

Serverless inference across 200+ open models with per-model cache-read rates, plus on-demand and spot GPU instances.

This page has not passed inetGeek's publishing gate yet:

- pricing_model was verified 48 days ago; the limit for this fact is 30.
- flagship_input_price was verified 48 days ago; the limit for this fact is 30.
- flagship_output_price was verified 48 days ago; the limit for this fact is 30.
- budget_input_price was verified 48 days ago; the limit for this fact is 30.
- context_window was verified 48 days ago; the limit for this fact is 30.
- prompt_caching was verified 48 days ago; the limit for this fact is 30.
- max_vram was verified 48 days ago; the limit for this fact is 30.
- free_tier was verified 42 days ago; the limit for this fact is 30.
- minimum_paid_price was verified 42 days ago; the limit for this fact is 30.
- regions was verified 42 days ago; the limit for this fact is 30.
- max_output_tokens was verified 42 days ago; the limit for this fact is 30.
- batch_discount was verified 42 days ago; the limit for this fact is 30.
- rate_limits was verified 42 days ago; the limit for this fact is 30.
- free_offer_type was verified 42 days ago; the limit for this fact is 30.
- soc2 was verified 42 days ago; the limit for this fact is 30.
- hipaa_eligible was verified 42 days ago; the limit for this fact is 30.
- gdpr_data_residency was verified 42 days ago; the limit for this fact is 30.
- encryption_at_rest was verified 42 days ago; the limit for this fact is 30.
- rbac was verified 42 days ago; the limit for this fact is 30.
- private_networking was verified 42 days ago; the limit for this fact is 30.
- dedicated_infrastructure was verified 42 days ago; the limit for this fact is 30.
- gpu_hourly_price was verified 41 days ago; the limit for this fact is 30.