We just increased the limits on free models in Requesty! - Free tier: 50 → 200 requests/day - Paying customers: 200 → 1,000 requests/day More room to test, build, and ship without thinking about the limit.

With Requesty, you can set budgets for teams, users, and individual API keys. You’ll also get alerted before usage turns into an unexpectedly large invoice. Teams shouldn’t have to log into every provider or rely on a spreadsheet just to keep tabs on spend.

From 1% to 17% in eight months. DeepSeek, GLM, Qwen, Kimi and LongCat now account for nearly 1 in 5 successful requests running through the Requesty AI Gateway. Chinese open-weight models are no longer a niche part of the model mix.

My requesty usage is outperforming my github commits. Autonomous agents are taking over

Managed model routing without the black box. With Requesty Managed Policies, you get: → One model ID → Visible endpoint priority → Automatic fallbacks → EU-focused @eu policies See exactly where your requests can go, while Requesty handles the routing. Video