Gemini 2.5 Flash
API ID gemini-2.5-flash
gemini-2.5-flash is a Google model, released June 2025. It has a 1,048,576-token context window and up to 65,536 output tokens. It takes image input and supports function calling, structured outputs and reasoning. Standard price: $0.30 input and $2.50 output per 1M tokens.
Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.
- Status
- Active
- Released
- June 2025
- Shutdown
- none announced
- Replacement
- —
No deprecation or shutdown date has been announced as of October 15, 2026.
Free tier: in place when tracking began (October 7, 2026) (source) · All free models
Benchmarks
Scores as each source published themComparing with Gemini 2.0 Flash, the previous model in this line. A score is compared only with the same benchmark from the same source, at the same setting where both have it. Full comparison: prices, limits, features
Arena
| Arena | Gemini 2.5 Flash | Gemini 2.0 Flash | Change | Rank | Date | Source |
|---|---|---|---|---|---|---|
TextBy category
| 1409 ±2 | not rated | 150 of 415 125,545 votes | Oct 13, 2026 | source | |
| Text: Coding | 1424 ±4 | not rated | 191 of 410 26,365 votes | Oct 13, 2026 | source | |
| Vision | 1215 ±5 | not rated | 82 of 165 60,112 votes | Oct 9, 2026 | source |
Rated as gemini-2.5-flash. Ratings come from people voting between two anonymous answers; Text and Vision are style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.
On cloud platforms
All platform dates| Platform | Platform ID | State | Shutdown | Time left | Replacement | Source |
|---|---|---|---|---|---|---|
| Google Cloud Vertex AI | gemini-2.5-flash | Active | Oct 20, 2026 | 5 days | gemini-3.8-flash or gemini-3.5-flash-lite or gemini-3.1-flash-lite | source |
Read daily from each platform's own pages. The shutdown date and countdown on this page use Google's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.
Features
Compare models| Feature | Value | Since | Source |
|---|---|---|---|
| Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup. | Supported | in place when tracking began (October 6, 2026) | source |
| Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result. | Supported | in place when tracking began (October 6, 2026) | source |
| Prompt cachingA prompt prefix you send again and again (system prompt, documents, tools) is cached, so later requests cost less and start faster. | Supported | in place when tracking began (October 6, 2026) | source |
| Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests. | Supported | in place when tracking began (October 6, 2026) | source |
| Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read. | Supported | in place when tracking began (October 6, 2026) | source |
| Reasoning / thinkingThe model can work through a problem step by step before it answers: usually better answers to hard questions, at the cost of more tokens and time. | Supported | in place when tracking began (October 6, 2026) | source |
| Built-in web searchThe company's API can search the web for the model during a request and cite its sources; you don't need a search service of your own. | Supported | in place when tracking began (October 6, 2026) | source |
| Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word. | 1,048,576 tokens | in place when tracking began (October 6, 2026) | source |
| Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word. | 65,536 tokens | in place when tracking began (October 6, 2026) | source |
Not published by Google: PDF input, Fine-tuning, temperature parameter, top_p parameter, logprobs.
Price history
USD per 1M tokens, standard tierWe started recording this model's prices on Oct 1, 2026. The history grows with each daily check.
Show as a table
| From | Type | Price |
|---|---|---|
| Oct 1, 2026 | Input | $0.30 |
| Oct 1, 2026 | Output | $2.50 |
Prices
USD per 1M tokens, every type and band, by tier| Type | Modality | Price $/1M | In effect |
|---|---|---|---|
| Standard | |||
| input | audio | $1.00 | |
| input | text/image/video | $0.30 | |
| cached input | audio | $0.10 | |
| cached input | text/image/video | $0.03 | |
| output | — | $2.50 | |
| cache storage per hour | — | $1.00 | |
| Batch | |||
| input | audio | $0.50 | |
| input | text/image/video | $0.15 | |
| cached input | audio | $0.10 | |
| cached input | text/image/video | $0.03 | |
| output | — | $1.25 | |
| cache storage per hour | — | $1.00 | |
| Flex | |||
| input | audio | $0.50 | |
| input | text/image/video | $0.15 | |
| cached input | audio | $0.10 | |
| cached input | text/image/video | $0.03 | |
| output | — | $1.25 | |
| cache storage per hour | — | $1.00 | |
| Priority | |||
| input | audio | $1.80 | |
| input | text/image/video | $0.54 | |
| cached input | audio | $0.18 | |
| cached input | text/image/video | $0.054 | |
| output | — | $4.50 | |
| cache storage per hour | — | $1.80 | |
Changelog
Changes we detected on Google's pagesNo changes recorded yet.
Email alerts
Get an email if gemini-2.5-flash changes
We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving Google's model list.
No password: one email to confirm, and you can unsubscribe any time. Privacy
Last checked · Sources: Google deprecations, Google pricing, Google models, Google aliases, Google api models