tokenstat
tokenstat

Google: Gemini 2.5 Flash Lite Preview 09 2025

gemini/gemini-2.5-flash-lite-preview-09-2025 · rates as of · Benchmarks · Plans · Calculator

Low-latency Gemini model for high-volume multimodal and agent workloads

Cheapest input
$0.09
$/MTok · models.dev
Cheapest output
$0.36
$/MTok
Context
1.0M
tokens
Offers
5
2 sources

Price changes

Cheapest list input/output only. Not a daily candle chart: rates move rarely, so this is an event log. Arrow down means cheaper.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ dropOutput $0.4 → $0.36
  • ↓ dropInput $0.1 → $0.09

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestgemini-2.5-flash-lite-preview-09-2025Jiekou.AI$0.09$0.36$01.0M
models.devgemini-2.5-flash-lite-preview-09-2025302.AI$0.1$0.4$01M
models.devgemini-2.5-flash-lite-preview-09-2025NanoGPT$0.1$0.4$01.0M
LiteLLMgemini/gemini-2.5-flash-lite-preview-09-2025$0.1$0.4$0.01
LiteLLMgemini-2.5-flash-lite-preview-09-2025$0.1$0.4$0.01

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: video
  • In: audio
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-01Released: 2025-09-26Family: gemini-flash-lite

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash