Why companies look for an alternative to Vercel AI Gateway
From Vercel AI Gateway’s own pricing and documentation, checked 7 November 2026:
- Company rules are metered: team-wide ZDR is $0.10 per 1,000 requests, and a team-wide provider allowlist $0.10 per 1,000 successful requests on Pro and Enterprise.
- Residency covers inference only: regional inference is opt-in, and Vercel says it doesn't pin where your request reaches AI Gateway; the request can terminate and be processed in any Vercel region. Image, video, speech and realtime models are not pinned.
- Provider retention is not filtered by default: by default, AI Gateway does not route based on the data retention policy of providers.
- Budgets can run over: Vercel says a budget is a soft cap, not a hard limit, the request that crosses it still completes, and spend on your own provider keys is not counted in any budget.
- Identity and audit cost extra: SAML SSO is a $300 a month add-on on Pro, and Directory Sync and Audit Logs are Enterprise-only.
What Standard Compute does differently
A single API gives you frontier and open-source models, and it routes each step to the cheapest model that can do it and the cheapest provider fast enough to serve it.
Vercel AI Gateway passes token prices through and leaves the model choice and fallback order to your code. Standard Compute does the model choice for you: routine agent steps go to a model priced for that work, the hard step goes to a frontier model, and each request is served by the cheapest provider that meets the latency and tokens-per-second bar. You pay a flat monthly plan per person or app.
Control is set once for the company:
Processing in Europe
Set a Europe rule for your company, a team or a single key, and every request, including retries and fallbacks, is served only by approved European inference endpoints. If no European endpoint can serve it, the request is refused before your prompt is sent. Our EU gateway terminates TLS and runs in Finland, and your account data is stored in Frankfurt.
Zero data retention
Turn on zero data retention for your company, a team or a key, and every request is routed only to inference endpoints that commit to keeping no copy of your data. Teams and keys inherit the requirement and can never switch it off underneath you.
No training
Standard Compute never trains on your prompts or outputs. With a region rule or zero retention turned on, every request goes only to providers that commit not to train on it.
Single sign-on
Connect Microsoft Entra ID or any SAML identity provider so your people sign in with their work accounts. Employees sign in to Claude Desktop and Claude Code with their Microsoft work account through our EU gateway, and access follows your Entra groups through SCIM provisioning.
Teams and keys
Organize your company into teams, invite colleagues by email, and give every person and every app its own key, all under one company account.
Budgets
Every person and app gets a fixed monthly budget that never overruns, and you can set spending caps per key and for the whole company. Optional top-off from a prepaid company balance keeps critical agents running.
Allow-lists
Choose exactly which inference providers may handle your data, for the whole company, a team or a single key. New providers are never added without an admin's approval, and fallbacks can never route around your list. Decide which models each key can use.
Audit
Every admin change is recorded with before and after values, and you can export a record of every request showing the model, the provider that served it and the region rule in force, kept for 12 months.
Contract
Sign our Data Processing Agreement in the dashboard. It commits us to no training on your data, no retention of your content, and breach notification within 72 hours. We publish every sub-processor and give you 14 days' notice before adding a new one.
Standard Compute and Vercel AI Gateway compared
| Standard Compute | Vercel AI Gateway | |
|---|---|---|
| Pricing | Flat monthly plan per person or app with no per-token surprises; Stripe invoices with your company name and VAT number | No markup on tokens; prepaid credits; team-wide ZDR and provider allowlist $0.10 per 1,000 requests each; Pro $20 a month, Enterprise custom |
| Cost routing | Each step goes to the cheapest model that can do it and the cheapest provider fast enough to serve it | Ordered provider and model fallbacks you configure |
| Models | Claude, GPT, Gemini and open models (GLM, DeepSeek, MiniMax, Kimi) through one API | Many vendors through credits or your own keys |
| Processing in Europe | Europe rule per company, team or key; retries and fallbacks stay on approved European endpoints; refused before sending if none qualifies | Opt-in regional inference for supported models; gateway entry point not pinned |
| Zero data retention | Per company, team or key; lower levels cannot switch it off | Per request, or team-wide at $0.10 per 1,000 requests |
| Training on your data | Never trains on prompts or outputs | Disallow-prompt-training setting; default not published |
| Single sign-on | SAML SSO, Microsoft Entra ID included; Claude Desktop and Claude Code sign-in with a Microsoft work account, SCIM from Entra | SAML SSO $300 a month on Pro, included on Enterprise; Directory Sync on Enterprise |
| Teams and keys | Teams, roles, a key per person and per app | Team roles; project-level roles on Enterprise |
| Spend limits | Fixed monthly budget per key; requests are refused once it is used; caps per key and per company | Budgets per team, project, key and user; soft cap; your own provider keys not counted |
| Provider and model allow-lists | Provider allow-list per company, team or key; new providers need an admin; models chosen per key | Per-request filter, or team-wide allowlist at $0.10 per 1,000 successful requests |
| Audit log | Admin log with before and after values; request export with model, provider and region rule, kept 12 months | Audit logs on Enterprise; request logs kept 30 days |
When Vercel AI Gateway fits
Vercel AI Gateway fits a product team that ships on Vercel, wants pass-through token prices on credits, and sets fallbacks in code, without a residency or hard-budget requirement.
Moving from Vercel AI Gateway to Standard Compute
Standard Compute’s API runs on stdcmpt.com. https://eu.stdcmpt.com is our EU gateway in Finland.
- Create a company workspace and set the rules once for the company: a Europe rule, zero data retention, and the providers and models you approve. Teams and keys inherit them.
- Map Vercel AI Gateway keys and user budgets to Standard Compute keys, one per person and per app, each with its own monthly budget.
- Change the base URL from
https://ai-gateway.vercel.sh/v1tohttps://eu.stdcmpt.com/v1and swapAI_GATEWAY_API_KEYfor a Standard Compute key. Model IDs keep thevendor/modelform. - Move
onlyfilters and fallback orders out of request options and into the provider allow-list. - Point Claude Code at
https://eu.stdcmpt.comin place ofhttps://ai-gateway.vercel.sh/claude-code. - Connect Microsoft Entra ID or your SAML identity provider so your people sign in with their work accounts, and set up Claude Desktop and Claude Code sign-in with Microsoft work accounts.
# Before
OPENAI_BASE_URL=https://ai-gateway.vercel.sh/v1
OPENAI_API_KEY=$AI_GATEWAY_API_KEY
# After: Standard Compute EU gateway
OPENAI_BASE_URL=https://eu.stdcmpt.com/v1
OPENAI_API_KEY=YOUR_STANDARD_COMPUTE_KEYfrom openai import OpenAI
client = OpenAI(
base_url="https://eu.stdcmpt.com/v1",
api_key=os.environ["STANDARD_COMPUTE_API_KEY"],
)
# "standardcompute" sends each step to the cheapest
# model that can do it. Or pin a model:
# model="anthropic/claude-sonnet-5.5"
client.chat.completions.create(
model="standardcompute",
messages=messages,
)# Claude Code adds /v1/messages itself
export ANTHROPIC_BASE_URL=https://eu.stdcmpt.com
export ANTHROPIC_AUTH_TOKEN=YOUR_STANDARD_COMPUTE_KEY
claudeQuestions
Is there a Vercel AI Gateway alternative with hard spend limits per developer?
Every person and app gets a fixed monthly budget that never overruns, and you can set spending caps per key and for the whole company. Optional top-off from a prepaid company balance keeps critical agents running.
Does zero data retention cost extra on Standard Compute?
Turn on zero data retention for your company, a team or a key and every request is routed only to inference endpoints that commit to keeping no copy of your data. It is part of the plan, with no per-request fee.
Can we keep EU requests in Europe from the first hop?
Our EU gateway terminates TLS and runs in Finland, and your account data is stored in Frankfurt. With a Europe rule, every request, including retries and fallbacks, is served only by approved European inference endpoints.
Do we need an Enterprise plan for SCIM and audit logs?
Connect Microsoft Entra ID or any SAML identity provider, with SCIM from Entra for Claude Desktop and Claude Code. Every admin change is recorded with before and after values, and the request record is kept for 12 months.
How do we migrate from Vercel AI Gateway?
Create a company workspace and set your rules, then change the base URL from https://ai-gateway.vercel.sh/v1 to https://eu.stdcmpt.com/v1 and swap the key. AI SDK and OpenAI SDK code stays the same.
Set up your company
Create a company workspace, invite your team and set your rules from the dashboard. Security questionnaires and procurement questions go to contact@standardcompute.com.
Create a company workspaceor write to contact@standardcompute.com
Sources (checked 7 November 2026)
- AI Gateway pricingvercel.com
- Vercel pricingvercel.com
- Regional inferencevercel.com
- Zero data retentionvercel.com
- Budgets and spend limitsvercel.com
- Logsvercel.com
- SAML SSOvercel.com
- Audit logvercel.com
- AI Gateway overviewvercel.com
- Claude Code with AI Gatewayvercel.com