Gemini 1.5 Flash
Google's fast, cheap 1M-context model — being superseded by Gemini 2.5 Flash for new projects.
Pricing
Input$0.075 ≤128k, $0.15 >128k / 1M
Cached input$0.018 / 1M
Output$0.30 ≤128k, $0.60 >128k / 1M
Deprecated for new projects.
Cost bandBudget
Free tierFree tier in AI Studio.
Limits
Context window1M
Max output8,192
Knowledge cutoffSep 2024
DeploymentGemini Developer API, Vertex AI
OpenAI-compatible APINo
ModalitiesText, Image, Audio, Video, PDF input
Where it fits
Best forLegacy long-context pipelines still on the 1.5 generation.
Business fitMigrate to Gemini 2.5 Flash for better quality and similar pricing.
Capabilities
Function callingGroundingCaching
Benchmark scores
Composite64 / 100
Coding60 / 100 (LiveCodeBench)
Reasoning64 / 100 (GPQA Diamond)
Long context82 / 100 (RULER 1M)
Vision62 / 100 (MMMU)
Instruction following66 / 100 (IFEval)
Editorial aggregate of published benchmark results as of Jan 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 checkedJan 10, 2026
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.