cuna inference
Pick The Model. Pay Per Token.
Serverless. Metered by the token.
Available in production
Sign in to the console, add prepaid inference credit in Payments, and create an inference key in API keys. Call the OpenAI-compatible Chat Completions API from your app or agent. No Cuna SDK required.
Account onboarding may apply. Requests require credit and are subject to key limits and available capacity.
- GLM-5.2Context 1M · Coding + reasoning · Z.ai's flagship, served lossless~280tok/sinput$1.00/Mcached in—output$4.00/MShow the request ›Hide the request ›glm-5.2 · production
curl https://inference.getcuna.com/v1/chat/completions \ -H "Authorization: Bearer $CUNA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "glm-5.2", "messages": [{"role": "user", "content": "Hello"}]}'
- Kimi K3Context 1M · Reasoning · Vision · Moonshot's 2.8T hybrid MoE~135tok/sinput$2.50/Mcached in—output$12.50/MShow the request ›Hide the request ›kimi-k3 · production
curl https://inference.getcuna.com/v1/chat/completions \ -H "Authorization: Bearer $CUNA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "kimi-k3", "messages": [{"role": "user", "content": "Hello"}]}'
USD per million · throughput approximate