tokenstat
tokenstat
Google

Google: Gemini 2.5 Flash

gemini/gemini-2.5-flash · rates as of · list price from ai.google.dev · How this catalog is built · Benchmarks

Fast Gemini workhorse for multimodal apps where latency and price matter

List input
$0.15
$/MTok · Google
List output
$0.6
$/MTok
Context
1.1M
tokens
Sources
4
39 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $2.50 → $0.71
  • ↓ lowerInput $0.3 → $0.09

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
tokenstatgemini/gemini-2.5-flashGoogle$0.15$0.6$0.0151.1M
models.devcheapestgemini-2.5-flashQiHang$0.09$0.71$01.0M
models.devgoogle/gemini-2.5-flashKilo Gateway$0.15$1.25$0.0151.0M
LiteLLMgemini-2.5-flashN/A$0.15$0.6$0.015N/A
LiteLLMgemini/gemini-2.5-flashN/A$0.15$0.6$0.015N/A
LiteLLMgoogle.gemini-2.5-flashN/A$0.15$0.6$0.015N/A
LiteLLMoci/google.gemini-2.5-flashN/A$0.15$0.6$0.015N/A
models.devgoogle/gemini-2.5-flashPoe$0.21$1.80$0.0211.1M
models.devgemini-2.5-flashJiekou.AI$0.285$2.38$0.02851.0M
models.devgemini-2.5-flashCortecs$0.299$2.49$0.0291.0M
models.devgemini-2.5-flashAIHubMix$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashCloudflare$0.3$2.50$0.031M
models.devgoogle/gemini-2.5-flashFastRouter$0.3$2.50$0.031.0M
models.devgemini-2.5-flashGoogle$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashImpossibl$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashMerge Gateway$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashNEAR AI Cloud$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashOfox$0.3$2.50$0.031.0M
OpenRoutergoogle/gemini-2.5-flashOpenRouter$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashOrcaRouter$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashStandard Compute$0.3$2.50$0.031.0M
models.devgoogle/gemini-2.5-flashVercel AI Gateway$0.3$2.50$0.031M
models.devgoogle/gemini-2.5-flashZenMux$0.3$2.50$0.031.0M
models.devgemini-2.5-flash302.AI$0.3$2.50$01M
models.devgemini-2.5-flashAbacus$0.3$2.50$0.031.0M
models.devgemini-2.5-flashAuriko$0.3$2.50$0.031.0M
models.devgemini-2.5-flashFrogBot$0.3$2.50$0.0751.0M
models.devgemini-2.5-flashGoogle Vertex AI$0.3$2.50$0.031.0M
models.devgemini-2.5-flashHelicone$0.3$2.50$0.0751.0M
models.devgemini-2.5-flashModelis$0.3$2.50$01.0M
models.devgemini-2.5-flashNanoGPT$0.3$2.50$0.031.0M
models.devgemini-2.5-flashSAP AI Core$0.3$2.50$0.031.0M
models.devgemini/gemini-2.5-flashCrossModel$0.3$2.50$0.031.0M
models.devdatabricks-gemini-2-5-flashDatabricks$0.3$2.50$0.031.0M
LiteLLMdeepinfra/google/gemini-2.5-flashN/A$0.3$2.50$0.03N/A
LiteLLMreplicate/google/gemini-2.5-flashN/A$0.3$2.50$0.03N/A
LiteLLMvercel_ai_gateway/google/gemini-2.5-flashN/A$0.3$2.50$0.03N/A
LiteLLMdatabricks-gemini-2-5-flashN/A$0.3$2.50$0.03N/A
LiteLLMdatabricks/databricks-gemini-2-5-flashN/A$0.3$2.50$0.03N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: audio
  • In: video
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2025-01Released: 2025-06-17Output limit: 66K tokensFamily: gemini-flash

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload