Gemini API free tier: eligibility and data use
Only certain Gemini API models have a free tier. Check model eligibility, projec…
The allocation resets daily, not monthly. Neurons are not request counts, and some models require paid billing.
The documented free allocation is 10,000 Neurons daily, resetting at 00:00 UTC. Our old monthly description was incorrect. Neurons are neither requests nor a universal token allowance.
Some models require paid billing. Paid-plan overage and associated Worker, storage or networking resources need separate checks.
Choose a model available to your plan, then use an AI binding or the REST API. Keep credentials server-side. Start with a short request and inspect actual Neuron usage in the dashboard.
Convenient for tools already on Workers. Estimate model consumption before batch jobs; a free allowance is not a capacity guarantee.
Public pricing documentation reviewed; no live inference run is claimed.