NorthStar AI Inference
NorthStar AI Inference is an OpenAI-compatible REST API providing access to open-source large language models hosted on dedicated GPU infrastructure in London, UK. AVAILABLE MODELS: - Qwen2.5-14B — best quality, ideal for complex reasoning, analysis, and content generation - LLaMA 3.1-8B — fast and efficient, ideal for high-volume automation tasks - Mistral-7B — lightweight, optimised for…
1 subscribers
3 endpoints
The in-depth APIMemo review for this API hasn't been published yet —
the data below comes straight from the public marketplace listing.
NorthStar AI Inference endpoints
| Method | Endpoint | Description |
|---|---|---|
| GET |
List Models /v1/models |
Returns all available models |
| POST |
Create Embeddings /v1/embeddings |
Generate vector embeddings using nomic-embed-text |
| POST |
Chat Completions /v1/chat/completions |
Generate text using Qwen2.5-14B or LLaMA 3.1-8B |
NorthStar AI Inference pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | 10 / minute |
|
| PRO Recommended | $15 / month | 30 / minute |
|
| ULTRA | $45 / month | 60 / minute |
|
