gemini-2.5-flash-liteGemini 2.5 Flash Lite (gemini-2.5-flash-lite) by Google catalog entry on Newton’s AI API gateway.
Newton’s exposes one customer-facing gateway route. Supplier and upstream routing details are kept internal.
| Route | Status | Input /M | Output /M | Cache read /M |
|---|---|---|---|---|
| Newton’s gateway OpenAI-compatible API | Unavailable | — | — | — |
Activity records the price used for each request. Cached input is shown separately when it is available.
Latency and throughput history are still collecting. Newton’s will show percentile, time window, and sample size once enough production observations exist.
Availability history is not yet published. Current catalog state is shown without converting a single verification run into an uptime claim.
Current catalog availability and billing status are shown below. Reported-model ID checks are not independent proof of the underlying model’s provenance.
Browse models or check availability again after this model is available.
Use the OpenAI-compatible API with the exact model ID.
curl https://newtons.dev/api/v1/responses \
-H "Authorization: Bearer $NEWTONS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gemini-2.5-flash-lite","input":"Hello from Newtons"}'Request-level tokens, cost, model identity, and latency appear in your Activity after you make a request.
Open Activity →Compare gemini-2.5-flash-lite against other frontier models served through Newton’s unified OpenAI-compatible gateway: