NEWMEN
← back to all models

Google: Nano Banana (Gemini 2.5 Flash Image)

google/gemini-2.5-flash-image

Googleclosed-weight33K context2 providers

Cheapest provider

$0.30 / 1M

Google

Fastest provider (p95)

274 tok/s

Google AI Studio

Intelligence (composite)

Not a chat-completion model

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$0.3000$2.50007778ms / 12526ms151 / 225 tok/s99.94%99.9%
Google AI Studiofull· unknown$0.3000$2.5000934ms / 9674ms175 / 274.1 tok/s100.00%100.0%

“—” 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).

How Atlas routes Google: Nano Banana (Gemini 2.5 Flash Image)

  • 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: Nano Banana (Gemini 2.5 Flash Image) that’s currently Google at $0.30/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.