Why companies look for an alternative to Portkey
From Portkey’s own pricing and documentation, checked 7 November 2026:
- A new owner: Portkey's site says Portkey is now PRISMA AIRS AI Gateway, and enterprise calls are booked through Palo Alto Networks.
- You still buy every model yourself: an Integration is a secure vault for your API keys, such as your OpenAI key or AWS Bedrock credentials, so each provider contract, quota and invoice stays with you.
- Identity and audit are Enterprise-only: SSO and SCIM provisioning are Enterprise features, and audit logs are an Enterprise plan feature. Enterprise is custom-priced.
- Budgets are on the top tier: key management with budgeting and rate limiting support is marked Enterprise, and workspace budget policies are available on the Enterprise Self Hosting plan only.
- Log-based pricing below Enterprise: Production is $49 a month for 100k recorded logs, plus $9 per additional 100k requests, and Portkey says it is not recommended for organizations requiring data residency guarantees.
- An EU-hosted SaaS region is not published. Data residency is offered through hybrid deployment, where the data plane runs in your VPC and Portkey hosts the control plane.
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.
Portkey routes the requests you configure and then you pay each provider's list price. 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 Portkey compared
| Standard Compute | Portkey | |
|---|---|---|
| Pricing | Flat monthly plan per person or app with no per-token surprises; Stripe invoices with your company name and VAT number | Free developer tier; Production $49 a month for 100k recorded logs; Enterprise custom; model usage 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 | Conditional routing, fallbacks and load balancing you configure |
| Models | Claude, GPT, Gemini and open models (GLM, DeepSeek, MiniMax, Kimi) through one API | The providers you connect with 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 | EU-hosted SaaS region not published; hybrid data plane in your VPC on Enterprise |
| Zero data retention | Per company, team or key; lower levels cannot switch it off | Depends on each provider contract you bring |
| Training on your data | Never trains on prompts or outputs | Depends on each provider contract you bring |
| Single sign-on | SAML SSO, Microsoft Entra ID included; Claude Desktop and Claude Code sign-in with a Microsoft work account, SCIM from Entra | SSO (OIDC, SAML 2.0) and SCIM on Enterprise |
| Teams and keys | Teams, roles, a key per person and per app | Workspaces; role-based access on Pro and Enterprise |
| Spend limits | Fixed monthly budget per key; requests are refused once it is used; caps per key and per company | Budgets and rate limits on Enterprise |
| Provider and model allow-lists | Provider allow-list per company, team or key; new providers need an admin; models chosen per key | Model allow-lists at org and workspace level; tier not published |
| Audit log | Admin log with before and after values; request export with model, provider and region rule, kept 12 months | Audit logs on Enterprise |
| DPA | Signed in the dashboard | Not published |
When Portkey fits
Portkey fits a team that already holds its own provider contracts and wants an observability and guardrail layer on top, inside the Palo Alto Networks security stack.
Moving from Portkey 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.
- Recreate each Portkey workspace as a team, and each Portkey API key as a Standard Compute key with its own monthly budget.
- Change the base URL from
https://api.portkey.ai/v1tohttps://eu.stdcmpt.com/v1and drop thex-portkey-*headers. Provider choice moves from headers and configs into the provider allow-list. - 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://api.portkey.ai/v1/chat/completions \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-H "x-portkey-provider: @openai-prod" \
-H "Content-Type: application/json" \
-d '{"model": "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
What is a good enterprise alternative to Portkey now that it is part of Palo Alto Networks?
Standard Compute is a gateway that includes the models: Claude, GPT, Gemini and open models through one API, routed to the cheapest capable model and provider, with a Europe rule, zero data retention, Entra SSO, per-key budgets, provider allow-lists and an audit log set self-serve.
Portkey vs LiteLLM vs Kong AI Gateway: which suits a regulated company?
All three govern provider keys you bring yourself. Standard Compute is the option that also supplies the models under one DPA, with a Europe rule that keeps retries and fallbacks on approved European endpoints and refuses a request before sending if none qualifies.
Do we need our own OpenAI and Anthropic contracts with Standard Compute?
No. One Standard Compute account gives you Claude, GPT, Gemini and open models through one API, under one DPA you sign in the dashboard.
How do we migrate from Portkey?
Create a company workspace and set your rules, then change the base URL from https://api.portkey.ai/v1 to https://eu.stdcmpt.com/v1, use a Standard Compute key and remove the x-portkey headers.
Does Standard Compute have SSO and SCIM?
Connect Microsoft Entra ID or any SAML identity provider so your people sign in with their work accounts, and Claude Desktop and Claude Code access follows your Entra groups through SCIM provisioning.
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)
- Portkey pricingportkey.ai
- Plan feature comparisonportkey.ai
- Model Catalogportkey.ai
- Audit logsportkey.ai
- Budget policiesportkey.ai
- SSOportkey.ai
- Hybrid deployment architectureportkey.ai
- Inference API headersportkey.ai
- Claude Code with Portkeyportkey.ai