Engineering notes and product updates
Notes from the team building Kunavo's AI API gateway — model picks, pricing decisions, Stripe and SDK plumbing.
- Review·May 24, 2026·7 min read
Image models shootout — Nano Banana Pro vs GPT-Image-2 vs Nano Banana 2
Three of the strongest image models on Kunavo — Nano Banana Pro, GPT-Image-2, and Nano Banana 2. Best text-in-image rendering, best prompt fidelity, best value — plus real per-image cost. Pick the right one for the right use case.
- Engineering·May 24, 2026·9 min read
How Kunavo fails over: the four layers between an upstream error and your client
The whole failover path, with the constant behind each number: a circuit breaker that skips a failing channel before the request is sent, up to three cost-ordered hops inside one request, a stream gate that refuses to commit a 200 that turns into an error, and a four-minute backstop for an upstream that never answers.
- Guide·May 24, 2026·8 min read
Anthropic prompt caching — cut 90% off your input bill in 30 minutes
The full picture: how cache_control works, why the OpenAI format needs Kunavo to set the breakpoints for you, the 4-breakpoint pattern for agent loops, what silently breaks caching, and how to verify your hit rate is non-zero. Includes Kunavo cache rates per model.
- Guide·May 23, 2026·6 min read
Migrating from OpenAI to Kunavo in 10 minutes — Python, Node, LangChain, Vercel AI SDK
Four flavors of OpenAI integration, the one-line change each needs to start running through Kunavo, and a smoke-test that costs less than a cent.
- Playbook·May 23, 2026·8 min read
AI API cost optimization — five techniques that actually cut the bill
Prompt caching, model tiering, output caps, parallelism, retry hygiene — with runnable code for each and realistic per-technique savings ranges. Stack them and you cut 70–80%.
- Guide·May 23, 2026·6 min read
Calling Claude with the OpenAI SDK — change one line, keep your codebase
Anthropic's SDK is great, but the ecosystem standardized on OpenAI's. Here's how to call Claude Opus 4.7, Sonnet 4.6 and Haiku 4.5 with the unmodified OpenAI Python and Node SDKs — streaming, tool use, vision included.
- Guide·May 23, 2026·7 min read
Veo 3 and Sora API quickstart — text-to-video and image-to-video in five minutes
Your first Veo 3 video generation calls through an OpenAI-style API: text-to-video, image-to-video with first/last frame control, file uploads, and a production-ready Python and Node example. Veo 3 is live today; Sora is on the roadmap on the same endpoint. No waitlist, no per-provider billing.
- Announcement·May 23, 2026·4 min read
Launching Kunavo — one OpenAI-compatible API for every frontier model, under official price
Why we built a Stripe-native AI API gateway: lower than upstream pricing, one bill across Claude, Gemini, GPT-Image, Veo, pay-as-you-go from a $10 top-up.