PrimeIntellect

Prime Intellect offers both hosted and externally routed inference. Its public policies do not establish prompt retention, training guarantees, or processing locations for externally routed inference; do not assume zero retention or exclusion from training.

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Prices are per million tokens. TTFT is the observed time to first token. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using PrimeIntellect via the API

Call a model served by PrimeIntellect using its displayed model ID, including the provider suffix when selection is supported.

No PrimeIntellect models are currently available for explicit selection, so requests pinning this provider will fail until availability returns.

For models with provider selection, append :primeintellect to the model ID, set "provider": "primeintellect" in the request body, or send an X-Provider: primeintellect header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

See the API documentation for provider preferences, price-aware routing, and error behavior.