gemini-3.5-flash-lite
vertex_ai-language-models ↗ · 1049K ctx · 3 providers · updated 2026-08-05 00:15 UTC
The board shows this model's cheapest measured offer ($0.850/1M); the smaller figure under it is the mean of the 4 offers listed below ($0.850/1M). Add those up and divide — it matches. 24h token volume (27B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| vertex_ai-language-models | Pricebook (LiteLLM) | $0.300 | $2.50 | — | — | — | Official list |
| gemini | Pricebook (LiteLLM) | $0.300 | $2.50 | — | — | — | Official list |
| openrouter-best | OpenRouter | $0.300 | $2.50 | — | — | — | API-measured |
| requesty | Requesty | $0.300 | $2.50 | — | — | — | API-measured |
Volume trend
Last 11 days: 45B → 27B (-39%); range 0–110B tokens/day. Source: OpenRouter public rankings; refreshed hourly.
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gemini-3.5-flash-lite.json. Free reuse requires attribution to tkx.org.
FAQ
How much does gemini-3.5-flash-lite cost?
Cheapest measured offer right now: $0.3/1M input, $2.5/1M output via vertex_ai-language-models — across 3 tracked providers, refreshed hourly.
Who serves gemini-3.5-flash-lite?
3 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is gemini-3.5-flash-lite used?
gemini-3.5-flash-lite routed 27B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.