Serves hosted open models and gateway access to third-party models through one OpenAI-compatible API, with rerank and classify endpoints and a CLI.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Chat Completions
Use Prime Inference to send OpenAI-style chat completion requests to hosted or gateway models: ‹what you need›
- List Models
Use Prime Inference to list available model IDs: ‹what you need›
- Classify and Score
Use Prime Inference to classify and score content: ‹what you need›
Install the CLI
pip install prime
Setup guide: docs.primeintellect.ai/inference/overview
Call the API
https://api.pinference.ai/api/v1
Auth An API key from Prime Intellect
Setup guide: docs.primeintellect.ai/inference/overview
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APICLI
- Auth
- API Key
- Skills
- 4
Skills
Chat Completions
Sends OpenAI-style chat completion requests to hosted or gateway models by catalog ID with one Prime API key.
List Models
Lists available model IDs, serving type and pricing through the models endpoint or the prime inference models command.
Rerank Results
Orders search results by relevance to a query with the hosted Qwen3 Reranker through the Rerank API.
Classify and Score
Classifies and scores content with hosted evaluation models such as Clef through the Classify and Evaluations APIs.