Gemini 2.5 Flash

Google · Gemini 2.5 · workhorse · Stable model, latest update October 2025 · gemini-2.5-flash

Gemini 2.5 family:Gemini 2.5 Pro·Gemini 2.5 Flash·Gemini 2.5 Flash-Lite

Google's price-performance model for low-latency, high-volume tasks that still need reasoning and tools.

Pricing

Input$0.30 text/image/video, $1 audio
Cached input$0.03 text/image/video, $0.10 audio
Output$2.50

Batch pricing cuts input to $0.15 and output to $1.25.

Cost bandBalanced
Free tierFree tier available with limits.

Limits

Context window1,048,576 checked Jul 19, 2026
Max output65,536
Knowledge cutoffJune 2025
DeploymentGemini Developer API and Google AI Studio
OpenAI-compatible APINo
ModalitiesText, Image, Audio, Video input

Where it fits

Best forHigh-volume assistants, multimodal pipelines, and cost-controlled agents.
Business fitUsually the Google default when budget and throughput matter more than absolute model quality.

Capabilities

ThinkingCachingBatch APICode executionFile searchFunction callingGroundingStructured outputs

Benchmark scores

Composite78 / 100
Coding76 / 100 (LiveCodeBench)
Reasoning79 / 100 (GPQA Diamond)
Long context82 / 100 (RULER 1M)
Vision83 / 100 (MMMU)
Instruction following79 / 100 (IFEval)

Editorial aggregate of published benchmark results as of Sep 1, 2025. These are not independent measurements run by this site.

Change history

No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.

Data

Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/google/gemini-2.5-flash

Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.

Open in the comparison table JSON API