Curious: How does Cursor manage its infra? Does it use providers like Groq, Fireworks.ai or Together.ai? If not, how do they manage the rate limits and scale model provisioning?
Just generally curious.
Curious: How does Cursor manage its infra? Does it use providers like Groq, Fireworks.ai or Together.ai? If not, how do they manage the rate limits and scale model provisioning?
Just generally curious.