Posts tagged "Agent-runners"

OpenAI’s ChatGPT Images 2.5 models are now available through Netlify’s AI Gateway and Agent Runners with zero configuration required. Use gpt-image-2.5-flare or gpt-image-2.5-sunburst to generate images for your applications.

Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using the gpt-image-2.5-flare model:

import OpenAI from 'openai';
const ai = new OpenAI();

export default async (req, context) => {
    const response = await ai.images.generate({
        model: 'gpt-image-2.5-flare',
        prompt: 'A golden retriever working at a laptop in a sunny startup office',
        size: '1024x1024',
        quality: 'low',
        output_format: 'jpeg',
        output_compression: 80
    });

    const imageBuffer = Buffer.from(response.data[0].b64_json, 'base64');

    return new Response(imageBuffer, {
        status: 200,
        headers: {
            'content-type': 'image/jpeg',
            'cache-control': 'no-store'
        }
    });
};

Both ChatGPT Images 2.5 models are available across standard Functions, Background Functions, Scheduled Functions, Edge Functions, and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure.

Learn more in the AI Gateway documentation and Agent Runners documentation.

Agent Runners can now scope ambitious prompts for new projects to create a partial working project and provide next steps within the available credit budget.

Previously, a brand new project could use up its credit budget before the agent finished for ambitious prompts, leaving the run marked Cancelled partway through.

Now, your agent scopes the work more intelligently. It builds out part of the project and shares a plan for next steps, so you can preview a working version within your new project credit budget instead of the run stalling out.

Learn more in Make changes with Agent Runners.

OpenAI’s GPT-6 Astra model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required.

Use the OpenAI SDK directly in your Netlify Functions without managing API keys or authentication. AI Gateway handles everything automatically. Here’s an example using GPT-6 Astra with the Responses API:

import OpenAI from 'openai';

export default async () => {
  const openai = new OpenAI();

  const response = await openai.responses.create({
    model: 'gpt-6-astra',
    input: 'Give a concise explanation of how AI works.',
  });

  return Response.json(response);
};

GPT-6 Astra is also available across Background Functions, Scheduled Functions, and Edge Functions. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure.

Learn more in the AI Gateway documentation and Agent Runners documentation.

Google’s Gemini 3.8 Flash model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required.

Use the Google GenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Gemini 3.8 Flash model:

import { GoogleGenAI } from '@google/genai';

export default async () => {
    const ai = new GoogleGenAI({});

    const response = await ai.models.generateContent({
        model: 'gemini-3.8-flash',
        contents: 'How can AI improve my coding?'
    });

    return Response.json(response);
};

Gemini 3.8 Flash is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure.

Learn more in the AI Gateway documentation and Agent Runners documentation.

Anthropic’s Claude Fable 5.1 model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required.

Use the Anthropic SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Claude Fable 5.1 model:

import Anthropic from '@anthropic-ai/sdk';

export default async () => {
    const anthropic = new Anthropic();

    const response = await anthropic.messages.create({
        model: 'claude-fable-5-1',
        max_tokens: 4096,
        messages: [
            {
                role: 'user',
                content: 'How can AI improve my coding?'
            }
        ]
    });

    return new Response(JSON.stringify(response), {
        headers: { 'Content-Type': 'application/json' }
    });
};

Claude Fable 5.1 is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure.

Learn more in the AI Gateway documentation and Agent Runners documentation.

Private projects on Netlify will now show a pre-launch toolbar so you can share your project for review and run audits using AI checks before you make your project public.

Private projects and agent runs require a Credit pricing plan. If you’re on a Legacy pricing plan, you will not have access to the pre-launch toolbar. Audits consume credits like any other agent run.

For public projects, new projects created on a Free plan on or after August 19, 2026 show a Powered by Netlify badge to all visitors.

The badge is configurable for each project through your project configuration settings.

To turn the Netlify badge on or off for all visitors of your site:

1. Go to Project configuration > General > Powered by Netlify badge and turn it on or off.

Additionally, any visitor can hide the badge for themselves, and that choice is stored locally on their browser and never reaches Netlify.

All projects created before August 19, 2026 have the badge off by default.

Users on a Credit-based Personal and Pro plans can also turn the badge on or off per-project. For these plans, the badge is always off by default.

Release timeline

We’re rolling both overlays out gradually over the next few weeks, so a project that qualifies may not have them yet.

Learn more about the pre-launch toolbar and the Powered by Netlify badge in the Netlify documentation.

Agent Runners can now ask you clarifying questions before they start building. When a few details could significantly improve the result, the agent pauses and asks instead of guessing.

How clarifying questions work

Say you start with something broad, like “Build a tracker dashboard.” Previously the agent had to make every call for you: what the dashboard should track, whether entries should be editable and saved to a database or live in the code as a read-only placeholder, whether the look should be dark and high-contrast or light, clean, and editorial. Now it can ask, and you can answer directly where the agent run works.

Answer, skip, or add your own context

Answering questions is always optional so you can answer the ones you have opinions about and skip the rest. Or you can skip all questions and let the agent decide. Finally, you can always add context in your own words alongside your answers.

In our testing, even a few quick answers make the first build noticeably sharper and saves credits you’d otherwise spend on course corrections.

Once you answer, the run continues as usual: the agent writes the code, works with Netlify’s platform features, and creates a Deploy Preview you can review and iterate on.

Learn more

Clarifying questions work with every agent and model available in Agent Runners.

Try it out and see how to use Agent Runners in our docs.

Google’s Gemini 3.7 Flash model is now available through Netlify’s AI Gateway and Agent Runners with zero configuration required.

Use the Google GenAI SDK directly in your Netlify Functions without managing API keys or authentication. The AI Gateway handles everything automatically. Here’s an example using the Gemini 3.7 Flash model:

import { GoogleGenAI } from '@google/genai';

export default async () => {
    const ai = new GoogleGenAI({});

    const response = await ai.models.generateContent({
        model: 'gemini-3.7-flash',
        contents: 'How can AI improve my coding?'
    });

    return Response.json(response);
};

Gemini 3.7 Flash is available for all Function types and Agent Runners. You get automatic access to Netlify’s caching, rate limiting, and authentication infrastructure.

Learn more in the AI Gateway documentation and Agent Runners documentation.

Through a new partnership with OpenRouter, you can now choose OpenCode as an AI agent with Agent Runners. OpenCode allows you to choose many different AI models, including Kimi, DeepSeek, and GLM.

Learn more about our OpenRouter partnership through the Netlify blog on open models.

Previously, you could only choose Claude, Gemini, or Codex as your AI agent, but now you can choose the OpenCode agent, which offers even more models from different AI providers.

Requests made through OpenCode are only routed to model providers with a Zero Data Retention (ZDR) policy, so your prompts and outputs are never stored.

AI model selection

As part of this release, you can now also specify which model any agent uses with Agent Runners. Previously, Claude, Gemini, and Codex agents all automatically chose a model for the task you prompted with Agent Runners.

Agents can still auto-select a model for you, but now you can also choose different models for your agents, with these preferences saved just for you on your device.

This means you can experiment with which AI models best fit your needs.

To open your AI model options for Agent Runners, select agent near your prompt box.

Choosing the best AI model for your needs

To help you choose the best AI model for your needs, within Agent Runners you can browse details about each model, including a link to learn more, a visual way to compare cost across all supported models with a 1-5 dot scale, and the option to set an effort level for that model.

To get the most out of your credits, consider the following strategies:

• Use a more expensive, capable model to help you plan your project updates and design a clear prompt with Agent Runners’ ask mode, then switch to a cheaper model to implement the changes.
• Experiment with using different AI models for different tasks.
• Be explicit about the functionality you want when using models that are cheaper or set to a lower effort level. These models may fill in placeholder functionality. For example, a model might render a contact page without fully setting up working Netlify Forms, so the page looks complete but doesn’t actually work as expected.

Learn more

To learn more, check out our docs:

• Agent Runners overview
• Make changes with Agent Runners