Why companies look for an alternative to Cloudflare AI Gateway
From Cloudflare AI Gateway’s own pricing and documentation, checked 7 November 2026:
- No regional processing for AI Gateway: the Data Localization Suite matrix marks AI Gateway as not supported for Regional Services, with Customer Metadata Boundary in progress, and says jurisdictional restrictions for its logs are not supported today.
- Prompts are logged by default: logs are enabled by default for each gateway and can include the prompt and response. You opt out per request with the
cf-aig-collect-logheader. - Zero data retention is narrow: on Cloudflare's own page, ZDR only applies to Unified Billing requests that use Cloudflare-managed credentials, so it does not cover requests with your own provider keys.
- A fee on billed usage: a 5% fee is applied to all credits purchased through Unified Billing, and credits can only be bought by credit card.
- Directory sync is Enterprise-only: dashboard SCIM provisioning is only available to Enterprise customers.
- Limits per gateway: requests billed through Cloudflare are capped at 200 requests per 60 seconds per gateway.
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.
Cloudflare AI Gateway proxies the model you name in each request; routing rules, fallbacks and budget nodes are yours to build. 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 Cloudflare AI Gateway compared
| Standard Compute | Cloudflare AI Gateway | |
|---|---|---|
| Pricing | Flat monthly plan per person or app with no per-token surprises; Stripe invoices with your company name and VAT number | Gateway free on all plans; 5% fee on Unified Billing credits, card only; or your own provider keys billed by each provider |
| Cost routing | Each step goes to the cheapest model that can do it and the cheapest provider fast enough to serve it | Dynamic routes with conditional, percentage and budget nodes, and fallback lists you configure |
| Models | Claude, GPT, Gemini and open models (GLM, DeepSeek, MiniMax, Kimi) through one API | Providers through your own keys or Unified Billing |
| Processing in Europe | Europe rule per company, team or key; retries and fallbacks stay on approved European endpoints; refused before sending if none qualifies | Regional Services not supported for AI Gateway; log jurisdiction restrictions not supported |
| Zero data retention | Per company, team or key; lower levels cannot switch it off | Unified Billing requests with Cloudflare-managed credentials only |
| Training on your data | Never trains on prompts or outputs | Not published |
| Prompt logging | Request records hold metadata only, never prompts or outputs | On by default; prompts and responses can be logged; opt out per request |
| Single sign-on | SAML SSO, Microsoft Entra ID included; Claude Desktop and Claude Code sign-in with a Microsoft work account, SCIM from Entra | Dashboard SSO on all plans; SCIM on Enterprise |
| Spend limits | Fixed monthly budget per key; requests are refused once it is used; caps per key and per company | Spend-limit rules per gateway by provider, model or metadata; requests get a 429 |
| Provider and model allow-lists | Provider allow-list per company, team or key; new providers need an admin; models chosen per key | Not published as an allow-list; content guardrails screen prompts and responses |
| Audit log | Admin log with before and after values; request export with model, provider and region rule, kept 12 months | Cloudflare account audit logs, kept 18 months; a per-request record of serving provider and region rule: Not published |
When Cloudflare AI Gateway fits
Cloudflare AI Gateway fits a team already on Cloudflare that holds its own provider keys and wants free caching, analytics and rate limiting in front of them, without a residency requirement.
Moving from Cloudflare 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.
- Create a key for each person and each application, each with its own monthly budget.
- Change the base URL from
https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compattohttps://eu.stdcmpt.com/v1, drop thecf-aig-*headers, and use one Standard Compute key inAuthorization. Model IDs keep thevendor/modelform. - Move spend-limit rules to per-key budgets and company caps, and fallback lists to the provider allow-list, so they apply without code.
- Point Claude Code at
https://eu.stdcmpt.comand removeANTHROPIC_CUSTOM_HEADERS. - 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
curl https://gateway.ai.cloudflare.com/v1/$ACCOUNT_ID/$GATEWAY_ID/compat/chat/completions \
-H "cf-aig-authorization: Bearer $CF_AIG_TOKEN" \
-H "Authorization: Bearer $PROVIDER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "openai/YOUR_MODEL", "messages": [...]}'
# After: Standard Compute EU gateway
curl https://eu.stdcmpt.com/v1/chat/completions \
-H "Authorization: Bearer $STANDARD_COMPUTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "standardcompute", "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 Cloudflare AI Gateway GDPR-friendly for EU customer data?
Cloudflare's own Data Localization Suite matrix does not list Regional Services for AI Gateway, and gateway logs are on by default. On Standard Compute you set a Europe rule for the company, a team or a key, and every request, including retries and fallbacks, is served only by approved European inference endpoints.
Does Standard Compute log our prompts?
We process your prompts in memory to serve each request and never write them to storage or logs. Request records hold metadata only: model, provider, tokens, cost and status.
Can we enforce zero data retention when we use our own keys today?
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.
Do we need a Cloudflare Enterprise plan for SCIM?
Not with Standard Compute. Connect Microsoft Entra ID or any SAML identity provider for the dashboard, and Claude Desktop and Claude Code access follows your Entra groups through SCIM provisioning.
How do we migrate from Cloudflare AI Gateway?
Create a company workspace and set your rules, then change the base URL to https://eu.stdcmpt.com/v1, remove the cf-aig headers and use a Standard Compute key. OpenAI-compatible client 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 pricingdevelopers.cloudflare.com
- AI Gateway limitsdevelopers.cloudflare.com
- Unified Billingdevelopers.cloudflare.com
- Loggingdevelopers.cloudflare.com
- Data Localization Suite compatibilitydevelopers.cloudflare.com
- Dashboard SSOdevelopers.cloudflare.com
- SCIM provisioningdevelopers.cloudflare.com
- Spend limitsdevelopers.cloudflare.com
- Dynamic routingdevelopers.cloudflare.com
- Audit logsdevelopers.cloudflare.com
- OpenAI-compatible endpointdevelopers.cloudflare.com
- Claude Code with AI Gatewaydevelopers.cloudflare.com