Gemini 2.5 Flash
Gemini 2.5 Flash is Google's first fully hybrid reasoning model, letting developers toggle thinking on or off and set thinking budgets to tune the balance between quality, cost, and latency, all on top of the fast, multimodal foundation of 2.0 Flash.
View API reference- Input and output price
- Prices from: Input $0.30, Output $2.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'google/gemini-2.5-flash', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Gemini 2.5 Flash by Google. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Gemini 2.5 Flash
Gemini 2.5 Flash
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Gemini 2.5 Flash through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Gemini 2.5 Flash request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. google/gemini-2.5-flash. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Gemini 2.5 Flash supports up to 65,536 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 1M-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
| — | URL, base64, Uint8Array | — | — | Sent as file parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK google provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['vertex', 'google'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);PDF input
Attach PDFs as file parts. Their contents count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', messages: [ { role: 'user', content: [ { type: 'text', text: 'Summarize this document.' }, { type: 'file', mediaType: 'application/pdf', data: 'https://example.com/document.pdf', }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'google/gemini-2.5-flash', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Google
| Model |
|---|
| 1M | 1.9 s | 412 tps | $0.75/M | $3.75/M | Read$0.08/M | $14/K+1 more | +3 |  | 09/02/2026 | |||||
| 1M | 0.8 s | 280 tps | $0.75/M | $3.75/M | Read$0.08/M | $14/K+1 more | +3 | | 08/13/2026 | |||||
| 1M | 0.5 s | 302 tps | $0.30/M | $2.50/M | Read$0.03/M | $14/K+1 more | +3 | | 07/21/2026 | |||||
| 1M | 0.6 s | 257 tps | $0.25/M | $1.50/M | Read$0.03/M | $14/K+1 more | +3 | | 05/07/2026 | |||||
| 1M | 0.6 s | 197 tps | $0.50/M+1 more | $3/M+1 more | Read$0.05/M | $14/K+1 more | +3 | | 12/17/2025 | |||||
| 1M | 0.2 s | 392 tps | $0.10/M | $0.40/M | Read$0.01/M | $35/K+1 more | +3 | | 06/17/2025 |
Copy link to headingAbout Gemini 2.5 Flash
Gemini 2.5 Flash builds directly on the 2.0 Flash foundation, carrying forward its speed and cost characteristics while adding a major reasoning upgrade. It launched in preview as Google's first fully hybrid reasoning model, a classification that sets it apart from both the 2.0 Flash generation and pure thinking models.
The hybrid design means thinking is not always on. You can disable thinking entirely to maintain 2.0 Flash response speed, or enable it and set thinking budgets to control how much deliberation the model applies before answering. With thinking on, 2.5 Flash shows meaningful performance improvements over the 2.0 generation on reasoning-intensive tasks. Its performance-to-cost ratio places it on the Pareto frontier, competitive on quality without requiring the full resource commitment of 2.5 Pro. This makes it well-suited for applications where some prompts are routine and some are complex, and you want a single model that adapts accordingly.
Gemini 2.5 Flash also integrates with tools including Google Search and code execution, and accepts multimodal input across text, images, video, and audio. The context window is 1M tokens, maintaining the long-context capability of the 2.0 Flash generation.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Thinking budgets affect token consumption and latency, so evaluate provider rate limits and pricing tiers with thinking-enabled requests before committing to a provider variant at production scale.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Gemini 2.5 Flash
Best for
- Workloads with mixed complexity: Applications that serve both simple requests and hard reasoning problems benefit from the ability to set per-request thinking budgets rather than paying for full reasoning on every call
- Reasoning-intensive pipelines: Multi-step math, science, coding, or logic tasks where 2.0 Flash's speed was sufficient but accuracy needs improvement
- Cost-conscious agentic applications: Need chain-of-thought planning but cannot afford 2.5 Pro pricing across high request volumes
- Coding and code transformation tasks: Benefit from the reasoning capabilities introduced in the 2.5 generation, including agentic code applications
- Multimodal reasoning: Images, video, or audio inputs that require more nuanced analysis than pattern matching
Consider alternatives when
- Deepest reasoning required: Highly complex problems with no speed or cost constraint, where 2.5 Pro's stronger benchmark scores may justify the premium
- Uniform high-volume inference: Entirely low-complexity workloads where thinking overhead adds cost without benefit, making 2.5 Flash-Lite or 2.0 Flash-Lite more appropriate
- Native image or audio output: 2.5 Flash outputs text only, so media generation needs a different model
Copy link to headingConclusion
Gemini 2.5 Flash introduces a new dimension of control to the Flash model family. You can dial reasoning depth from zero to a configured budget, matching compute expenditure to actual task complexity. It retains the efficiency that made Flash popular while unlocking the reasoning quality that previously required a heavier model.
Copy link to headingFrequently Asked Questions
What does "hybrid reasoning" mean for Gemini 2.5 Flash?
It means the model operates in two modes: with thinking disabled (behaving like a fast response model comparable to 2.0 Flash) or with thinking enabled at a configurable budget, where it reasons through the problem before generating an answer.
How do thinking budgets work?
You set a per-request parameter that controls how much deliberation the model applies before responding. A higher budget allows more reasoning steps, improving accuracy on complex tasks at the cost of more tokens and higher latency. A lower budget favors speed and cost.
If I disable thinking, how does 2.5 Flash compare to 2.0 Flash?
2.5 Flash outperforms 2.0 Flash even with thinking disabled. The 2.5 base model is stronger regardless of thinking mode.
Does Gemini 2.5 Flash support Google Search tool use?
Yes. Google Search and code execution are shared capabilities across all Gemini 2.5 models, including Gemini 2.5 Flash.
What is the context window for Gemini 2.5 Flash?
The context window is 1M tokens.
How is 2.5 Flash positioned relative to 2.5 Pro?
Gemini 2.5 Flash sits at the Pareto frontier of cost and performance. It delivers strong reasoning at a lower cost than 2.5 Pro, which targets complex tasks with strong benchmark scores.
Is Gemini 2.5 Flash generally available?
It launched in preview on March 20, 2025. Google later promoted it to stable general availability alongside 2.5 Pro as part of the Gemini 2.5 family expansion.