BriefsPricingAvailable now1 min read

Vercel cuts ai agent session costs by 67 percent

Vercel lowers ai agent session costs in the dashboard and Slack by restructuring context management and prompt caching.

Vercel cuts ai agent session costs by 67 percent — image from Vercel
Image: Vercel

Summary

Vercel lowered the average cost of ai agent sessions in the dashboard and Slack by 67 percent. The company rebuilt context management to use fewer tokens and improved prompt cache reuse. Billing rates remain the same, charging model inference rates plus a Vercel agent fee of $0.25 per million tokens.

What changed

  • Ai agent sessions in the dashboard and Slack now cost 67 percent less on average.
  • Context management was rebuilt to reduce tokens needed per session.
  • Prompt cache reuse has been improved.
  • The updates are live and require no user action.

Availability

Available now

“These improvements are live and require no action.”

Pricing

PlanPrice, as statedChecked
Vercel Agent fee$0.25 per million tokens“Paid sessions are billed at the model provider’s inference rates plus a Vercel Agent fee of $0.25 per million tokens.” source

Prices as stated by the company; we don’t convert or estimate.

Founder takeaway

These updates are live and require no action, so there is nothing for your team to do yet.

Source

VercelVercel Agent sessions now cost 67% less - Vercel

Announced Checked

Researched and drafted with AI from the official sources above, then checked automatically before publishing. Spotted a mistake? Tell us.

SharePost on XLinkedIn

Related

More briefs

All briefs
  1. GitHub includes GitHub Copilot in GitHub Enterprise subscriptions — image from GitHub

    PricingRolling out

    GitHub includes GitHub Copilot in GitHub Enterprise subscriptions

    GitHub Enterprise now includes access to GitHub Copilot for every licensed user when working with an account team.

    GitHub1 min read

  2. Vercel adds MiniMax M3.1 Flash AI model to AI Gateway, free until Oct 22 — image from Vercel

    PricingAvailable now

    Vercel adds MiniMax M3.1 Flash AI model to AI Gateway, free until Oct 22

    MiniMax's open-weight AI model for coding and agent work is free on Vercel AI Gateway until Oct 22, if MiniMax serves the request.

    Vercel1 min read

  3. Vercel adds sandbox plugin support for running Paseo AI agents — image from Vercel

    ToolAvailable now

    Vercel adds sandbox plugin support for running Paseo AI agents

    Paseo now supports running AI agents in the cloud using the Vercel Sandbox plugin.

    Vercel1 min read

One email, every Monday

Briefs are published here through the day. Monday Heist is the email: one useful AI workflow, the files to use it, and the catch. The first issue is being prepared; subscribers get it first. Free, and you can leave in one click.

One email. Every Monday.