Vercel AI Gateway vs LiteLLM
The question that decides it: Are the seats already on your invoice, and can you tolerate a gateway you cannot self-host?
Our verdict
Already shipping on Vercel with seats you are paying for anyway: the gateway is free at the margin and nothing here beats it on convenience. Not on Vercel, or unwilling to send prompts through a vendor you cannot self-host: LiteLLM, which costs nothing per request and runs wherever you put it.
Why
Both publish zero token markup and zero credit fee, which makes the fee comparison unusually clean: the question is seats against infrastructure. Vercel Pro is $20 per user per month, so a three-person team is $60 whether or not the gateway is used at all. LiteLLM is free, and our cost page assumes $40 a month of compute and database to run it — an assumption about your setup, not a published price. If you are already paying for the Vercel seats, the marginal cost of the gateway is zero and LiteLLM cannot beat that.
Vercel's add-on pricing is where the clean story gets complicated, and one line deserves naming: zero data retention is $0.10 per 1,000 requests on Pro and Enterprise. On most platforms in this catalogue ZDR is a setting; here it is metered. At the 250,000 requests on our cost page that is $25 a month on top of the seats, and a team-wide provider allowlist is another $0.10 per 1,000 successful requests. Neither is exotic governance — they are the kind of thing a security review asks for by default.
Deployment settles a lot of shortlists. Vercel AI Gateway is managed only and explicitly not air-gappable. LiteLLM is self-host only. There is no overlap, so if either constraint is hard for you, the comparison resolves before you reach the features. On provider breadth LiteLLM leads clearly with 140+ providers; Vercel publishes 200 to 350 models and no provider count.
The compliance columns favour Vercel on paper: SOC 2, a HIPAA BAA, zero data retention available and a 30-day retention window, all audited and published. LiteLLM publishes none of those, because there is no hosted service to audit — the posture is whatever your deployment has. That is not automatically worse, but it means you are the one producing evidence for the reviewer instead of forwarding a report.
Which one, concretely
Choose Vercel AI Gateway if
- You already ship on Vercel and the Pro seats are a sunk cost
- You want a gateway with no infrastructure to operate at all
- You need SOC 2 and a HIPAA BAA from the gateway vendor rather than from your own deployment
- You use the AI SDK and want the routing to be one configuration line
Choose LiteLLM if
- You are not paying Vercel for seats and do not want to start at $20 per user
- You need provider breadth — 140+ providers against an unpublished count
- You need air-gapped or fully self-hosted operation
- You want zero data retention as a setting rather than a per-request charge
What catches people out
- Vercel meters zero data retention at $0.10 per 1,000 requests — at 250,000 requests a month that is $25 on top of seats
- A team-wide provider allowlist is also metered, at $0.10 per 1,000 successful requests
- Vercel seats are per user, so the gateway gets more expensive as the team grows even if usage does not
- LiteLLM's enterprise features — SSO, RBAC, SCIM, audit logs — need a commercial licence with no published price
Side by side
3 of 10 fields differ, marked with a dot. Every figure links to the vendor page it came from. Blank values read Not published rather than No — silence from a vendor is not a negative answer.
| Field | Vercel AI Gateway | LiteLLM |
|---|---|---|
| Ease of leaving Derived score, higher is easier | 64/84 Some work to leave | 100/100 Easy to leave |
| Runs fully disconnected Air-gapped deployment | No | Yes |
| Content guardrails Content guardrails | No | Yes |
| Similar-question caching Semantic cache | No | Yes |
| SOC 2 audited SOC 2 audited | Yes | Not published |
| Will sign a HIPAA agreement HIPAA BAA | Yes | Not published |
| Does not retain your data Zero data retention | Yes | Not published |
| Settings can live in version control Declarative config-as-code | Not published | Yes |
| Separate keys per team or app Virtual keys | Yes | Yes |
| Automatic failover Automatic failover | Yes | Yes |
| GitHub stars GitHub stars | Not published | 57,500 |
Verified 3 days ago for Vercel AI Gateway and Verified 3 days ago for LiteLLM. Want more fields, or a third option in the mix? Open these two in the full comparison tool.
Common questions
Is Vercel AI Gateway free?
There is no token markup and no credit fee, but reaching it on a team requires Vercel Pro seats at $20 per user per month, and several governance features are metered separately — zero data retention and a provider allowlist are each $0.10 per 1,000 requests.
Can I self-host either of these?
Only LiteLLM. It is self-host only and can run air-gapped. Vercel AI Gateway is managed only and documented as not air-gappable.
Which is cheaper for a three-person team?
At the workload on our cost page, Vercel AI Gateway costs $60 a month in seats and LiteLLM costs an assumed $40 in infrastructure. If those seats already exist for hosting, Vercel's marginal cost is zero and it wins outright. Add metered zero data retention and Vercel rises by roughly $25.
Which supports more providers?
LiteLLM, with 140+. Vercel publishes a model catalogue of 200 to 350 but no provider count, so a direct provider comparison is not possible from published figures.