Change one URL
Point Claude Code or Codex at the gateway with its key; no code changes.
Agent Lab AI Gateway · Enterprise AI control plane
Claude, GPT, Gemini and 80-plus models behind one key. Decide which data may reach which model and who may spend how much before a call leaves; every call is on the record.
Rather read the docs first? See how to connect.
The basics
An AI gateway (or LLM gateway) is the control layer between a company and its AI models: every tool calls models through it, and it decides where data may go, which model answers and how much may be spent, and records each call.
Four questions IT asks first
What the records show feeds the next round of rules
01 Access
Point Claude Code or Codex at the gateway with its key; no code changes.
80-plus models from many makers, switchable any time, or held to a few.
Images, audio or tool calls go only to models that can handle them.
02 Control
The gateway enforces the rules, so nobody has to remember them.
Emails, phone numbers, card numbers, national IDs and API keys blocked or masked in requests and replies; add your own terms.
Hold a workspace, each key or a directory group to set models; keys also to source IPs.
By tag, end user, spend or rate, narrow the models and providers a request may use, or refuse it.
Prompts and replies never reach a database, log or trace; only metadata is kept.
03 Cost
| Task assessed as | auto: | auto | auto: |
|---|---|---|---|
| Extraction, rewriting, chat | Cheapest | Cheapest | Standard |
| Analysis, coding, planning | Cheapest | Standard | Stronger |
| Multi-step | Standard | Stronger | Stronger |
| Could not tell | Standard | Standard | Standard |
X-AgentLab-Routing: auto.Spend split by key, model, team and provider; export a month as CSV.
Daily savings against always using the strongest model, net of the assessment's own cost.
A sample shows whether each key's model fits its work; switch to a cheaper one in one click.
2% of requests answered by a cheaper model are rerun on the standard one and compared.
Real usage
Our own workspace, last 30 days as of 2026-10-29, numbers from the console's usage page.
04 Govern
Workspace
Team
Key
End user
Cost is held up front, so concurrent calls cannot overspend together.
Expiry, allowed models, source IPs, rotation without downtime; stored as hashes.
Groups from your enterprise SSO (OIDC) carry allowed models and a monthly budget.
Alerts at 80% and 100%, and when spend jumps to three times a usual day.
Multi-region companies
When a company has offices in Taiwan, Hong Kong or Singapore, IT and compliance ask first: where is data kept, who may use which models, and can we trace what happened.
Settings, usage and the audit trail stay in Google Cloud Taiwan; models run in each provider's cloud.
Guardrails check both what is sent and what the model replies, and can mask or refuse; off by default, turned on by IT.
Set the models and budget each office may use, per key or per enterprise SSO group.
The same key reaches open models such as DeepSeek, Llama, Mistral and gpt-oss, and you can self-host a model in your own project.
Each model provider has its own supported regions and usage policies; book a demo and we will confirm with you which models apply where your company operates.
Compare
| Hosting | Budget enforcement | Auto model choice | Best for | |
|---|---|---|---|---|
| Agent Lab AI Gateway | Run by us, or self-hosted per project | Held before sending | Auto by difficulty | Companies that do not want to run it |
| LiteLLM | Open source, self-hosted | Reserved before sending | Auto Router (beta) | Engineering teams that self-host |
| Portkey (now Prisma AIRS AI Gateway) | SaaS, hybrid, self-hosted | Per-key limits | Rule-based | Request logs and observability first |
| Cloudflare AI Gateway | Run by Cloudflare; core free | Charged after completion | Auto Router | Teams already on Cloudflare |
| Kong / Azure APIM | Extends existing API management | Kong: next request; Azure: tokens only | Load balancing | Teams already on them |
| TrueFoundry | SaaS; enterprise self-host | Per user or model | Weight, latency | Teams that also host models |
From each vendor's docs, checked 2026-10-21: LiteLLM, Portkey, Cloudflare, Kong, Azure, TrueFoundry.
FAQ
Self-hosting, a contract, or questions first? Book a demo:
Already have a workspace? Open the AI Gateway page in the console. The docs cover keys, limits and errors.
We'll email you to set a time.