Sign inGet API key

Compare Google Gemini 2.5 Flash with other AI models

See how Gemini 2.5 Flash from Google compares with other AI models on price, context length and features.

Chat with Gemini 2.5 Flash
1 model
Gemini 2.5 FlashGoogle

Google's first hybrid reasoning model with configurable thinking budgets; best price-performance for low-latency, high-volume tasks that require reasoning.

Overview

Overview for Gemini 2.5 Flash
MetricGemini 2.5 Flash
AuthorGoogle
TypeText
Context length1.05M tokens
Max output66K tokens
ReasoningYes
Input modalitiesTextImageAudioVideoFile
Output modalitiesText
ReleasedJun 17, 2025
Served byGoogle via Oxyy
APIOpenAI-compatible · Gemini/v1/chat/completions
  • Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

Pricing

Pricing for Gemini 2.5 Flash
MetricGemini 2.5 Flash
Input$0.120 /1M inputStandard $0.300
Output$1.00 /1M outputStandard $2.50
Cached input$0.012 /1M cachedStandard $0.030
Cache write$0.120 /1M cache writeStandard $0.300
Blended price (3:1 input:output)$0.340 /1M tokens
  • Includes the Launch Promo discount (60% off the standard price).

Performance

Performance for Gemini 2.5 Flash
MetricGemini 2.5 Flash
Latency (p50, 7 days)2.23 s
Time to first token (p50)1.94 s
Throughput (p50)714.3 tok/s
Tokens (7 days)281.2M
Visualize performance
Latency, daily median
Throughput, daily median
  • Gemini 2.5 Flash

Features

Features for Gemini 2.5 Flash
MetricGemini 2.5 Flash
Tool useYes
Structured outputsYes
Prompt cachingYes
StreamingYes
Web searchYes
Image inputYes

Activity

Activity for Gemini 2.5 Flash
MetricGemini 2.5 Flash
Tokens (30 days)950.1M tokens · last 30 days
Input tokens885.8M
Output tokens (excluding reasoning)57.0M
Reasoning tokens7.3M
Gemini 2.5 Flash950.1M tokens · last 30 days
  • Input 885.8M
  • Output (excl. reasoning) 57.0M
  • Reasoning 7.3M

Suggested models to compare

How this comparison is built

Prices are what Oxyy charges today; where a discount applies, the standard price is shown beside it. Context window, output limit, modalities and features come from the Oxyy model catalog. Latency, time to first token and throughput are medians measured on Oxyy traffic over the last 7 days (throughput from streaming requests only); a model with too little traffic shows a dash. Benchmark scores appear only with their source and date. Oxyy is an independent API gateway, not affiliated with the model vendors named on this page.