# Gemini 3 Flash

Pro-grade reasoning at flash speed: Gemini 3 Flash brings Gemini 3's intelligence to high-throughput applications where latency and cost cannot be compromised.

- **Model ID:** `google/gemini-3-flash`
- **Type:** chat
- **Providers:** vertex, google
- **Context window:** 1,000,000
- **Maximum output tokens:** 65,000
- **Pricing:** $0.5/1M input tokens, $3/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gemini-3-flash

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'google/gemini-3-flash',
  prompt: 'Why is the sky blue?'
})
```

## About

Gemini 3 Flash is Google's speed-optimized model in the Gemini 3 generation, combining Gemini 3's reasoning depth with the efficiency profile of the Flash tier. It outperforms Gemini 2.5 Pro across most benchmarks, meaning a speed-tier model now surpasses a previous-generation flagship. Gemini 3 Flash achieves this with meaningful gains in token efficiency over the 2.5 generation. See live metrics on this page for current throughput.

Thinking is first-class in Gemini 3 Flash. The `thinkingLevel` and `includeThoughts` provider options let you surface intermediate reasoning steps. This helps when debugging multi-step pipelines, constructing chain-of-thought datasets, or validating that Gemini 3 Flash reasons through a problem correctly. Set `thinkingLevel` to `high` when the task demands deeper inference and your latency budget allows it.

Because Gemini 3 Flash sits at the intersection of quality and throughput, it fits a wide range of real-world traffic patterns, from low-latency chat interfaces to batch document processing pipelines. Accessing it through AI Gateway adds observability, automatic retries, and provider failover without requiring a Google Cloud account.

## What to consider

Gemini 3 Flash supports configurable thinking levels (`high` included) via `providerOptions`, giving you direct control over how much reasoning compute the model applies per request.

## When to use

### Best For
- Real-time chat and assistant interfaces that require pro-level reasoning without high latency
- High-volume agentic pipelines where per-token cost directly affects operating expenses
- Step-by-step analysis tasks where surfacing intermediate reasoning (`includeThoughts`) adds value
- Applications previously bottlenecked by Gemini 2.5 Pro throughput limits
- Cost-sensitive production workloads that still require benchmark-competitive quality

### Consider Alternatives When
- Your task requires the absolute maximum reasoning depth regardless of cost or speed (consider `google/gemini-3-pro-preview` or `google/gemini-3.1-pro-preview`)
- You need native image generation output alongside text (consider `google/gemini-3-pro-image` or `google/gemini-3.1-flash-image-preview`)
- Budget and latency are the dominant constraint and task quality requirements are low (consider `google/gemini-3.1-flash-lite-preview`)
- You are building a pure image-generation pipeline with no language component

## Best for

- **Real-time chat and assistants:** Interfaces that require pro-level reasoning without high latency
- **High-volume agentic pipelines:** Per-token cost directly affects operating expenses
- **Step-by-step analysis:** Tasks where surfacing intermediate reasoning (`includeThoughts`) adds value
- **Throughput-bottlenecked apps:** Applications previously constrained by Gemini 2.5 Pro throughput limits
- **Cost-sensitive production workloads:** Production traffic where per-token cost matters but quality still has to stay benchmark-competitive

## Consider alternatives

- **Maximum reasoning depth:** Your task requires the deepest reasoning regardless of cost or speed (consider `google/gemini-3-pro-preview` or `google/gemini-3.1-pro-preview`)
- **Native image generation needed:** You require image output alongside text (consider `google/gemini-3-pro-image` or `google/gemini-3.1-flash-image-preview`)
- **Budget and latency dominate:** Task quality requirements are low (consider `google/gemini-3.1-flash-lite-preview`)

## Frequently asked questions

### What makes Gemini 3 Flash different from Gemini 2.5 Flash?

Gemini 3 Flash is built on the newer Gemini 3 architecture rather than Gemini 2.5. The generation change brings a substantial capability lift: Gemini 3 Flash surpasses Gemini 2.5 Pro on most benchmarks, so a speed-tier model in the 3 generation now exceeds the previous generation's flagship.

### Can I control how much the model thinks before answering?

Yes. You can set `thinkingLevel` (e.g., `'high'`) and `includeThoughts: true` inside `providerOptions.google` when using the AI SDK. This gives you visibility into intermediate reasoning steps.

### Does Gemini 3 Flash support streaming?

Yes. Use `streamText` from the AI SDK with `model: 'google/gemini-3-flash'` for streaming responses.

### Do I need a Google Cloud account to use this model on AI Gateway?

No. AI Gateway handles all provider authentication. You authenticate to AI Gateway using a Vercel API key or OIDC token and do not need to configure Google credentials separately.

### How does Gemini 3 Flash compare to Gemini 3 Pro on reasoning tasks?

Gemini 3 Pro targets the most challenging reasoning and agentic workflows. Gemini 3 Flash prioritizes speed and cost while still delivering pro-grade quality. The right tradeoff depends on your latency budget and task complexity.

### What is Zero Data Retention and does Gemini 3 Flash support it?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

### What token efficiency improvements does Gemini 3 Flash offer?

Gemini 3 Flash uses fewer tokens than the previous Gemini 2.5 generation on comparable tasks. Combined with lower per-token pricing, this lowers cost at scale for applications processing large request volumes.

### Is Gemini 3 Flash suitable for agentic multi-step workflows?

Yes. The model's combination of reasoning capability, token efficiency, and low latency makes it well-suited for agents that execute multiple tool calls or reasoning steps in sequence within a budget-constrained environment.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gemini-3-flash)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/models)
- [Provider pricing](https://cloud.google.com/vertex-ai/generative-ai/pricing)