Chrome Prompt API
Run Gemini Nano inside Chrome — on-device AI inference with no cloud round-trip
The Panel's Take
Chrome's Prompt API lets web developers call Gemini Nano — Google's compact, locally-running language model — directly from JavaScript, without any server requests after the initial model download. The API accepts text, audio (AudioBuffer or Blob), and visual inputs (images, canvas elements, video frames), returns streaming text responses, and supports JSON Schema-constrained structured output for reliable data extraction. Sessions are created via LanguageModel.create(), with each session maintaining a token-aware context window that prunes older messages automatically while preserving system prompts. The Prompt API complements other Chrome AI primitives including the Summarizer, Writer, Rewriter, Translator, and Language Detector APIs — all running fully on-device. Model requires 22GB+ free disk space for the initial download; subsequent use works offline. This is a meaningful shift for web AI. Developers can now build privacy-preserving AI features — local transcription, smart autocomplete, content classification, on-page summarization — without touching a cloud API or paying per-token costs. Currently supports English, Japanese, and Spanish. Available via Chrome's Origin Trial program with broader rollout expected through 2026.
Share this verdict
Chrome Prompt API verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/chrome-prompt-api-gemini-nano-on-device-browser-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare Chrome Prompt API with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/chrome-prompt-api-gemini-nano-on-device-browser-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/chrome-prompt-api-gemini-nano-on-device-browser-2026" alt="Chrome Prompt API Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/chrome-prompt-api-gemini-nano-on-device-browser-2026)<iframe src="https://shiporskip.io/embed/chrome-prompt-api-gemini-nano-on-device-browser-2026" title="Chrome Prompt API ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“The JSON Schema structured output is the feature I've been waiting for — finally you can extract clean data from user-typed text without a backend. The 22GB download is a real onboarding hurdle, but once the model is cached, the latency is basically zero compared to cloud APIs. This changes the math for privacy-sensitive consumer apps.”
“A 22GB model download as a prerequisite for a web feature is going to have terrible adoption outside of developer demos. Most users won't have that space or patience, and the English/Japanese/Spanish-only limitation rules it out for global products. Wait for the model to shrink before betting your product on this.”
“On-device inference in the browser is the endgame for consumer AI. No API keys, no latency, no data leaving the device — this is what private-by-default AI looks like. The browser becomes the AI runtime, and Google just got there first. The model size issue is a 2026 problem; by 2027 it'll be 2GB.”
“Real-time image and canvas analysis directly in the browser opens up creative tooling that wasn't possible without a backend. Think live design feedback, style detection from reference images, or on-the-fly alt-text generation — all without a cloud API call. The streaming responses make it feel snappy enough for interactive UX.”