NEWMEN
← back to all models

Google: Gemini 2.5 Flash Lite

google/gemini-2.5-flash-lite

Googleclosed-weight1.0M context3 providersIntelligence 55.1· est.

Cheapest provider

$0.10 / 1M

Google

Fastest provider (p95)

284 tok/s

Google AI Studio

Intelligence (estimated)

55.1

Family + generation + popularity + price tier

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
Googlefull· unknown$0.1000$0.4000713ms / 2491ms71 / 231 tok/s99.15%99.5%
Googlefull· unknown$0.1000$0.4000713ms / 2491ms71 / 231 tok/s98.64%99.5%
Google AI Studiofull· unknown$0.1000$0.4000603ms / 2167ms118 / 284 tok/s99.03%99.8%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence estimate

No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.

Want a curated score? File a benchmark report and we’ll add it to the next sync.

How Atlas routes Google: Gemini 2.5 Flash Lite

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Google: Gemini 2.5 Flash Lite that’s currently Google at $0.10/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.