High-throughput sub-second multimodal model with native 1M context at budget rates
gemini-2.5-flash| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.00022 | $0.00017 |
| Document Summarization | 10,000 | 2,000 | $0.00135 | $0.00079 |
| Codebase & Context Analysis | 100,000 | 20,000 | $0.0135 | $0.00788 |
| Batch Corpus Processing | 1,000,000 | 100,000 | $0.1050 | $0.0488 |
Ideal for production workloads demanding budget capabilities, deep context depth (1.05M tokens), and reliability from Google. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For Gemini 2.5 Flash, 1 million input tokens costs $0.075, while 1 million output tokens costs $0.30. If using prompt caching, repetitive input prefixes are discounted to $0.019 per million.
Gemini 2.5 Flash features a maximum context window of 1,048,576 tokens (~786,432 words), with a maximum output limit of 8,192 tokens per completion.
Gemini 2.5 Flash utilizes the Google Gemma SentencePiece (~256k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
Yes. Gemini 2.5 Flash supports prompt caching with a cached input rate of $0.019/1M (saving up to 75% on repeated input context).