Writing
The Kumo blog
How token-gateway pricing really works, drop-in migration, and the engineering behind it. No fluff — just the mechanics.
June 26, 2026
Kumo and OpenRouter: the honest comparison
Both are OpenAI-compatible gateways to many models. Here's how their operating models differ, including cases where a broader public catalog matters more.
June 25, 2026
Why Kumo's rate lands 30–50% below list — and how to check it
The lower rate is real, not a teaser. Here's what's guaranteed, what moves the number, and how to verify it yourself.
June 20, 2026
Indie developer: one balance for every side project
How a solo builder runs supported GPT, Claude and Gemini models on one prepaid balance. Full story coming soon.
June 19, 2026
Content & marketing: more drafts per dollar
How a small content team runs generation at Kumo's lower rate and caps spend per campaign. Full story coming soon.
June 18, 2026
AI agency: every client's volume on one balance
How an agency pools client volume, scopes a key per project, and bills cleanly from one dashboard. Full story coming soon.
June 17, 2026
Enterprise: one endpoint for the whole org
How a platform team gives every team LLM access through one endpoint, with per-team caps and one invoice. Full story coming soon.
June 16, 2026
Agent & automation builder: cheap, steady token throughput
How an automation builder runs millions of agent calls a month on one endpoint with scoped keys and manual provider retry. Full story coming soon.