Threshold billing now sends Pro teams a partial invoice mid-cycle once on-demand usage reaches a threshold, instead of holding all charges until the end of the billing period. Partial invoices and the end-of-cycle invoice add up to your total usage, so the same usage is never billed twice.

Learn more about partial invoices.

Claude Fable 5 from Anthropic is now available on AI Gateway. A Mythos-class model, Fable 5 is a notable step up over prior Claude models on long-running, ambiguous, multi-step tasks, executing end-to-end on work that previously required frequent human check-ins.

The model sustains productive output across multi-day runs and dependably dispatches parallel sub-agents, and lower effort settings often match what prior Claude models produced at their highest effort. Code review, bug-finding, and repository investigation are stronger, and first-shot correctness on complex problems is noticeably higher.

Fable 5 ships with blocking classifiers in place that refuse offensive cybersecurity, biology, and summarized-thinking extraction, because the model's capabilities in those areas introduce real misuse risk. Anthropic also does not support Zero Data Retention because some misuse patterns only become visible across cumulative requests. Prompts and completions are retained for 30 days and are not used to train Claude.

To use Fable 5, set model to anthropic/claude-fable-5 in the AI SDK.

1
import { streamText } from 'ai';
2

3
const result = streamText({
4
  model: 'anthropic/claude-fable-5',
5
  prompt: 'Investigate why p99 latency regressed and propose a fix.',
6
  providerOptions: {
7
    anthropic: {
8
      thinking: { type: 'adaptive' },
9
      effort: 'high',
10
    },
11
  },
12
});

AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, dynamic provider sorting by latency and cost, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.

Learn more about AI Gateway, view the AI Gateway model leaderboard or try it in our model playground.

AI costs are getting harder to forecast. As teams lean more on coding agents and other token-heavy workflows, a key can burn cost faster than anyone notices:

• Autonomous workflows that can loop or fan out without supervision

• Demos and prototypes that could catch unexpected traffic if shared or shipped

• Developers exploring or experimenting without a sense of per-model cost

Set a spend cap on any key, and AI Gateway rejects further requests on that key once the limit is exceeded, until the budget resets or you raise it. The cap applies to all AI Gateway providers and models running through the key, making it easier to consolidate and govern AI costs.

Link to headingAPI key budgets in the Vercel Dashboard

On the AI Gateway API Keys page, click Create Key, enable the Spend Quota option, enter a limit in dollars, and choose a refresh period.

You can also edit existing keys and add, change, or remove budgets by clicking the right hand side ... menu and Edit Key.

Link to headingAPI key budgets in the Vercel CLI

Create a budgeted API key programmatically via the Vercel CLI. The format is:

vercel ai-gateway api-keys create --name <NAME> --budget <DOLLARS> --refresh-period <PERIOD>

Pair a key with an optional refresh period (daily, weekly, monthly, or none) to scope the limit to a window. Each period resets at the start of its window in UTC.

Keys created programmatically will also appear in your team AI Gateway API Keys view, so you can see all keys in one place.

Read the API keys documentation for more information about setting and using budgets for API keys.

You can now use the Vercel CLI to search domains. Using the vercel domains search command, you can supply a domain name and retrieve availability and price results for all TLDs that Vercel supports.

~ vercel domains search acmesite --limit 5
> Domain        Availability  Purchase        Renewal
  acmesite.com  Unavailable   -               -
  acmesite.dev  Available     $13 / 1 year    $13 / 1 year
  acmesite.app  Available     $14.99 / 1 year $15 / 1 year
  acmesite.io   Available     $37.99 / 1 year $46 / 1 year
  acmesite.ai   Available     $160 / 2 years  $160 / 2 years
> To continue, run `vercel domains search acmesite --next eyJxdWVyeSI6ImFjbWVza...

You can also filter by TLD, apply sorting, and filter out unavailable domains.

1
vercel domains search acmesite --tld com --tld ai
2
vercel domains search acmesite --available
3
vercel domains search acmesite --order alphabetical
4
vercel domains search acmesite --format json
5
vercel domains search --help

Upgrade your Vercel CLI to version 54.10.1 to get started.

Vercel Sandbox now supports drives in private beta. Drives are persistent, attachable storage with a lifecycle independent from any sandbox.

Create a drive once, then mount it at a configurable path when starting a sandbox. When the sandbox stops, the drive remains available to attach to a later sandbox.

Install the beta SDK (@vercel/sandbox@beta) or beta CLI (sandbox@beta), then create and mount a drive:

1
import { Drive, Sandbox } from "@vercel/sandbox";
2

3
const drive = await Drive.getOrCreate({
4
  name: "agent-workspace",
5
});
6

7
const sandbox = await Sandbox.create({
8
  mounts: {
9
    "/workspace": {
10
      drive: drive.name,
11
      mode: "read-write",
12
    },
13
  },
14
});

Sandbox Drives are useful for:

• Keeping agent workspaces across disposable sandboxes

• Retaining cloned repositories, dependencies, and build outputs

• Managing data independently from the sandbox lifecycle

During the private beta, a drive can be mounted read-write by one sandbox at a time. Sandbox drives should not be used for production data while in private beta.

Sign up here to join the waitlist, and learn more in the docs.

The skills.sh API is now available. Authenticate with your project's Vercel OIDC token and start querying more than 600,000 skills from across the open-source ecosystem.

Search for skills, pull detailed info on any one, check its security audit, and more.

Vercel issues a short-lived token scoped to your team and project, rotated automatically, so there's no long-lived secret to leak or rotate. On each request, skills.sh verifies the token and applies a rate limit of 600 requests per minute per team and project.

1
import { getVercelOidcToken } from '@vercel/oidc';
2

3
const token = await getVercelOidcToken();
4
const res = await fetch('https://skills.sh/api/v1/skills?per_page=10', {
5
  headers: { Authorization: `Bearer ${token}` },
6
});

Read the skills.sh API documentation to get started.

The proliferation of agentic workflows means developers now regularly grant AI tools direct access to their infrastructure, use services that act autonomously, and build on platforms that themselves use AI to operate. We’ve updated our Terms of Service and Marketplace terms to clarify shared responsibility when actions on your account may be taken by AI, whether Vercel's own or a third-party tool you've connected, as well as other important updates detailed below.

Link to headingWhat is changing?

Link to headingAI Functionality and Third-Party Tools

Vercel's platform increasingly includes AI-powered services, including v0, Vercel Agent, WAF natural language rules, and AI Gateway. These services may take actions on your behalf. We've introduced two new concepts to make the responsibilities around this explicit:

AI Functionality refers to Vercel services that are AI-powered, that help you build AI products (like AI SDK), or that connect to AI providers (like AI Gateway).

Third-Party Tools refers to any non-Vercel tool, script, service, or automation (AI-powered or not) that you grant access to your Vercel account. This includes CI/CD pipelines, third-party agents, and integration scripts.

The key responsibilities:

• You control how AI Functionality behaves through your settings. Those settings define the scope of what AI Functionality can do on your behalf.

• You are responsible for reviewing and authorizing the actions AI Functionality takes, and for evaluating its outputs against your own requirements.

• If you grant a Third-Party Tool access to your Vercel account (e.g., giving it your API key), you are responsible for what it does, including any costs it incurs.

• You are responsible for actions taken by AI Functionality or Third-Party Tools on your behalf.

Link to headingBilling flexibility

We are updating our billing terms to reflect the expansion of our product surface area beyond subscription plans.

• Fees are no longer exclusively tied to a subscription plan. Services like AI Gateway credits can be purchased and charged independently.

• For non-subscription services, charges may occur at the time of purchase or top-up.

• If your account shows unusually high or suspicious usage, Vercel may charge accrued fees ahead of your regular billing cycle. Learn more about Partial Invoices.

We have also added a direct link to vercel.com/pricing in the terms.

Link to headingEnterprise Managed Accounts

Enterprise customers who have verified ownership of an email domain can now claim email addresses on that domain that are associated with existing Vercel accounts. If your account email falls within a claimed domain, Vercel will notify you and you'll have the option to update your email address. If the account was used for work with that organization, it may instead be added to their Team. In either case, the Enterprise customer does not gain access to your account or your content without your consent.

Link to headingRepresentations

Two new customer representations have been added:

• You confirm you have the rights to provide any third-party credentials or API keys to Vercel (for example, through Vercel Connect or other integrations).

• You confirm you are not subject to applicable OFAC sanctions.

Link to headingMarketplace

The Marketplace terms now introduce the concept of Authorized Users, which includes Third-Party Tools. Actions taken by Authorized Users are bound to you as the customer, and you are responsible for reporting any unauthorized Authorized User activity.

Link to headingPrivacy Policy

We have updated the Data Privacy Framework section. Previously, unresolved EU/UK/Swiss privacy complaints were directed to data protection authorities. We've now designated VeraSafe as our private complaint handler. Complaints can be submitted directly to VeraSafe before escalation to a regulator.

Link to headingFrequently asked questions

The full updated Terms of Service are at vercel.com/legal/terms. The Marketplace terms and Privacy Policy are linked from the same page.

Nemotron 3 Ultra from Nvidia is now available on Vercel AI Gateway.

Nemotron 3 Ultra is an open Mixture-of-Experts reasoning model built for orchestrating long-running agent workflows, with a 1M token context window. The model targets multi-turn agent workflows: planning, tool use, sub-agent delegation, and error recovery. Throughput reaches up to 350 tokens per second, with up to 30% lower cost on agentic tasks.

To use Nemotron 3 Ultra, set model to nvidia/nemotron-3-ultra-550b-a55b in the AI SDK.

1
import { streamText } from 'ai';
2

3
const result = streamText({
4
  model: 'nvidia/nemotron-3-ultra-550b-a55b',
5
  prompt: 'Plan and run a multi-step research task and synthesize a report.',
6
});

AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, dynamic provider sorting by latency and cost, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.

Learn more about AI Gateway, view the AI Gateway model leaderboard or try it in our model playground.