Vercel
Vercel Agent
A hosted agent whose coding workflows review pull requests, validate findings in a sandbox, and propose tested fixes.
Attributed output
GitHub public-attribution count, 2026-10-12
99.5K PRsAttributed outputGitHub public-attribution count, 2026-10-12Commits and PRs on public GitHub provably produced by this agent. Exact if it is visible through its own bot or workflow, an estimate if measured through attribution it declares (these can swing 30 to 40 percent between measurement runs at multi-million scale), and a floor either way.Index rank · all agents
of 47 agents · trailing 4 weeks PRs
#7Index rank · all agentsof 47 agents · trailing 4 weeks PRsRanked by agent-opened PRs in the trailing 4 complete weeks, matching the index. Agents without a tracked PR series follow, ordered by total attributed output. Other filters or sorts change the list position.n/a
Business signal
No sourced business metric
n/aBusiness signalNo sourced business metricPro / Enterprise + usage
Entry price
Inference tokens and platform usage
Pro / Enterprise + usageEntry priceInference tokens and platform usageNot published
GitHub stars
No public repo
Not publishedGitHub starsNo public repoNot published
npm demand/wk
Public npm counter
Not publishednpm demand/wkPublic npm counterWeekly package downloads as an install-demand floor; adjusted when the vendor's main install channel is no longer npm.Activity Over Time
Weekly attributed output on public GitHub. Output visible through the agent's own bot or workflow is exact; output measured through declared attribution is an estimate. Window: 2025-02-03 to 2026-10-05.
Market
Developer output
Public pull requests opened by Vercel Agent
Public PRs carrying explicit Vercel Agent task attribution. A conservative estimate: Vercel's shared automation also serves other products, so its broad activity is excluded. Reviews without an agent-authored PR are not counted.
Last full week (ending 2026-10-11): 2,009 agent-marked PRs (-4.2% week over week), search estimate.
Merge rate: 32.9% of its pull requests get merged (5,887 of 17,875 over 8 settled weeks, 2026-08-03 to 2026-09-27). The window ends about ten days back so recently-opened PRs have had time to merge.
GitHub review activity: 5.7% of its merged PRs had at least one GitHub review record before merging; the other 94.3% had none. This is a broad weekly signal and can include bot reviews; the human-review read below comes from the enriched PR sample.
Snapshot 2026-10-12, confidence Medium, tracked since 2026-06-09. Read the methodology.
- Index rank · all agents
- #7 of 47
- Demand share
- No public npm package
- Business signal
- No sourced business metric
- GitHub share
- No public repo
- npm channel
- No public npm package
Pricing And Economics
ExpandHide
Pricing snapshot: 2026-10-12. Check the vendor for current terms.
Inference at cost plus $0.25 per million tokens, on Vercel Pro or Enterprise.
- Entry price
- Pro / Enterprise + usage
- Top self-serve price
- n/a
- Pricing unit
- Inference tokens and platform usage
- Token transparency
- Token rate card
- Included usage
- No included code-review allowance.
- Overage path
- Provider inference, the Vercel token fee, and underlying product usage are billed separately.
Retail Token Equivalent
The Vercel fee is $0.25 per million tokens in addition to provider inference. There is no fixed token budget.
| Plan | Price | Allowance | Unit | Token / Overage Notes |
|---|---|---|---|---|
| Agent usage | Provider inference + $0.25/M tokens | Pay for code-review usage on an eligible Vercel plan. | Tokens |
Summary checked 2026-10-12.
Available on Vercel Pro and Enterprise. Agent usage bills provider inference at cost plus $0.25 per million tokens; underlying Vercel product charges also apply.
- The $0.25 per million tokens is a Vercel fee added to inference costs, not the total model price.
- Code reviews have no included usage allowance.
Product
Providers
Model families
Capabilities
Tradeoffs
- Requires a Vercel Pro or Enterprise plan.
- This listing covers coding and review workflows; the product also offers operational investigations.
- Provider model selection and BYOK are not publicly documented.