Does more efficient thinking mean lower quality outputs?

No. Performance stays the same while token consumption decreases. The model uses fewer tokens to reason through a problem without degrading output quality, which reduces cost per task.

What thinking level does this model support?

`medium` thinking level, configured via `thinking_level` in `providerOptions.google`. This provides finer control over the cost, performance, and speed tradeoff.

Is this model suitable for automated code review?

Yes. Software engineering quality improvements are a primary focus of the 3.1 update, making it well suited for code review, security analysis, and test generation.

How do I set the thinking level in the AI SDK?

Under `providerOptions.google` in your `streamText` or `generateText` call, set `thinking_level` to `low`, `medium`, or `high`.

Does Gemini 3.1 Pro Preview require its own Google API account?

No. AI Gateway manages all provider credentials. You connect using a Vercel API key or OIDC token.

What makes this model well-suited for finance and spreadsheet tasks?

Gemini 3.1 Pro specifically improves on finance and spreadsheet usability. These tasks involve structured numerical analysis, formula generation, and multi-step calculation that benefit from pro-tier reasoning.

When should I use Gemini 3.1 Pro versus Gemini 3.1 Flash for engineering tasks?

For complex multi-step engineering tasks where correctness of the reasoning chain matters, security audits, architectural planning, test generation, the Pro tier provides more thorough reasoning. For high-volume, more repetitive engineering tasks like code completion or linting at scale, Flash-tier models offer a better cost-to-quality ratio.

Google

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview advances software engineering and agentic workflows with targeted quality improvements for finance and spreadsheet applications, plus more efficient thinking that reduces token consumption while maintaining performance.

View API reference

Input and output price: Prices from: Input $2, Output $12, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'google/gemini-3.1-pro-preview',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out Gemini 3.1 Pro Preview 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 3.1 Pro Preview

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.

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Free Tier	Release Date

Google

Legal:Terms•Privacy

64K

7.4 s

105 tps

$2/M+3 more

$12/M+3 more

Read$0.20/M

$14/K+1 more

02/19/2026

Google Vertex AI

Legal:Terms•Privacy

64K

6.8 s

114 tps

$2/M+3 more

$12/M+3 more

Read$0.20/M

$14/K+1 more

02/19/2026

Getting started

Call Gemini 3.1 Pro Preview 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.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same Gemini 3.1 Pro Preview request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    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-3.1-pro-preview`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. Gemini 3.1 Pro Preview supports up to `64,000` 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
PDF	—	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.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['google', 'vertex'],
      },
    },
  });

  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.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    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.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    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.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    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.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'google/gemini-3.1-pro-preview',
    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

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

google/gemini-3.8-flash

1.9 s

412 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

09/02/2026

google/gemini-3.7-flash

0.8 s

280 tps

$0.75/M

$3.75/M

Read$0.08/M

$14/K+1 more

08/13/2026

google/gemini-3.5-flash-lite

0.5 s

302 tps

$0.30/M

$2.50/M

Read$0.03/M

$14/K+1 more

07/21/2026

google/gemini-3.1-flash-lite

0.6 s

257 tps

$0.25/M

$1.50/M

Read$0.03/M

$14/K+1 more

05/07/2026

google/gemini-3-flash

0.6 s

197 tps

$0.50/M+1 more

$3/M+1 more

Read$0.05/M

$14/K+1 more

12/17/2025

google/gemini-2.5-flash-lite

0.2 s

392 tps

$0.10/M

$0.40/M

Read$0.01/M

$35/K+1 more

06/17/2025

Copy link to headingAbout Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is the updated flagship in the Gemini 3.1 family, building directly on Gemini 3 Pro with quality improvements targeted at real-world production domains. Software engineering and agentic workflows are the primary areas of improvement, alongside enhanced usability for finance and spreadsheet applications.

The model introduces more efficient thinking. At the pro tier, input tokens are a significant cost factor in long agentic sessions. Better reasoning efficiency means the model works through complex tasks without generating proportionally more tokens, directly reducing per-task operating cost compared to Gemini 3 Pro.

For teams building developer tooling, code review automation, or financial analysis pipelines, Gemini 3.1 Pro Preview is designed for the level of structured reasoning those applications require.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: This model supports the medium thinking level via thinking_level in providerOptions.google, giving you control over the cost, performance, and speed tradeoff.
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 3.1 Pro Preview

Best for

Automated code review: Security vulnerability analysis and test suite generation
Agentic software engineering: Tasks requiring planning across multiple code changes
Financial and spreadsheet analysis: Modeling, formula generation, and structured numerical work
Pro-tier reasoning tasks: The efficient thinking improvement reduces per-task token cost
Long agentic sessions: Accumulated token consumption from reasoning steps is a cost concern

Consider alternatives when

Initial Gemini 3 Pro baseline: You need capabilities without the 3.1 updates (consider google/gemini-3-pro-preview)
Speed and cost at volume: Your primary need is efficiency at high throughput (consider google/gemini-3-flash or google/gemini-3.1-flash-lite-preview)
Image generation alongside reasoning: Your task requires native image output (consider google/gemini-3-pro-image)
Flash-tier reasoning is enough: Pro-tier capability is not required (consider google/gemini-3-flash)

Copy link to headingConclusion

Gemini 3.1 Pro Preview addresses the most common reasons teams hit limits with Gemini 3 Pro: token-heavy reasoning sessions in agentic workflows, and the need for more reliable performance in finance and structured data applications. The efficiency improvements in thinking make extended pro-tier reasoning more economically viable for sustained production deployments.

Copy link to headingFrequently Asked Questions

What improvements does Gemini 3.1 Pro Preview have over Gemini 3 Pro?
Three areas: quality improvements for software engineering and agentic workflows, enhanced usability for finance and spreadsheet applications, and more efficient thinking that reduces token consumption while maintaining performance.
Does more efficient thinking mean lower quality outputs?
No. Performance stays the same while token consumption decreases. The model uses fewer tokens to reason through a problem without degrading output quality, which reduces cost per task.
What thinking level does this model support?
medium thinking level, configured via thinking_level in providerOptions.google. This provides finer control over the cost, performance, and speed tradeoff.
Is this model suitable for automated code review?
Yes. Software engineering quality improvements are a primary focus of the 3.1 update, making it well suited for code review, security analysis, and test generation.
How do I set the thinking level in the AI SDK?
Under providerOptions.google in your streamText or generateText call, set thinking_level to low, medium, or high.
Does Gemini 3.1 Pro Preview require its own Google API account?
No. AI Gateway manages all provider credentials. You connect using a Vercel API key or OIDC token.
What makes this model well-suited for finance and spreadsheet tasks?
Gemini 3.1 Pro specifically improves on finance and spreadsheet usability. These tasks involve structured numerical analysis, formula generation, and multi-step calculation that benefit from pro-tier reasoning.
When should I use Gemini 3.1 Pro versus Gemini 3.1 Flash for engineering tasks?
For complex multi-step engineering tasks where correctness of the reasoning chain matters, security audits, architectural planning, test generation, the Pro tier provides more thorough reasoning. For high-volume, more repetitive engineering tasks like code completion or linting at scale, Flash-tier models offer a better cost-to-quality ratio.

Your use is subject to Google's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Gemini 3.1 Pro Preview

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Copy link to headingMore models by Google

Copy link to headingAbout Gemini 3.1 Pro Preview

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use Gemini 3.1 Pro Preview

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions