
Govern any OpenAI-compatible API
If a model service speaks the OpenAI API, Argent can govern it. Add it as an endpoint with its key in your vault, and the same approved list, redaction, budgets and signed record apply.
What Argent does with any OpenAI-compatible endpoint
Many model services copy the OpenAI API. Argent's standard API-key connection covers them, and new providers are data, not code.
- Standard API-key connection: any OpenAI-compatible service is governed with its key brokered from your vault.
- Provider settings as data: a platform admin can add a provider with its credential type, secret headers, fixed headers, host patterns and where the model is named, in the console's Credential Broker area.
- Same controls: approved models, access rules, redaction, budgets and the signed record work as they do for named providers.
How it connects
One endpoint, one key in your vault, and every agent points at Argent instead of the provider.
- Add the endpoint once. On the AI Providers page, one action creates the the provider endpoint with its credential. The provider key is written to your vault and Argent keeps only the vault reference.
- Register each agent with an owner. Every agent or app gets its own Argent key and a named human owner. Its Connect tab shows copy-paste setup and a VERIFY CONNECTION check.
- Point it at Argent. The agent's base URL becomes its route on the Argent gateway,
/<tenant>/<endpoint>/, and the Argent key takes the place of the provider key. - The gateway swaps keys on the way out. It removes the agent's Argent key, fetches the provider key from your vault and attaches it at egress, after checking the provider's certificate.
- Rotate in your vault. Every gateway replica drops the cached key, and no agent changes.
Your vault can be HashiCorp Vault or OpenBao, AWS Secrets Manager, CyberArk Conjur or Infisical. The agent never holds the provider key, so a leaked agent key is useless anywhere but Argent, and you can switch it off in one place. See Keyless Agents.
What you configure
Everything below is set once in the Argent console and applies to every agent that calls the provider through the gateway.
| Setting | Where | What it does |
|---|---|---|
| Approved models | Policy > Model and endpoint access | Default deny: a call is allowed only when the model is on the approved list. The list is platform AND tenant AND agent, and each layer can only narrow the one above. |
| Access rules | Same page | Allow or deny by provider, route type, model, hosted tools, function tools and output type, for the tenant, a department, a person or one agent. The narrowest rule wins, and a 7-day impact preview shows what a draft would change. |
| Sensitive data | DLP | Per entity type: redact and record, record only, or block the request. |
| Budgets and caps | Budgets | Budgets for the company, org, department, person and agent. Each request is priced and held against the budget before it leaves, and an emergency cap stops a runaway agent now. |
| Mode | Per control | Off, watch or enforce. Watch records what would have been refused and changes nothing on the wire. |
Start in watch, read what would have been refused, then switch on enforce. See Watch Before You Enforce.
One request, step by step
What happens between your agent and the provider, in order.
- The agent sends its request to its Argent route, carrying its own Argent key and nothing from the provider.
- Who is calling. Argent identifies the agent from its key and checks it may use this endpoint. The endpoint comes from the route the gateway matched, never from a header the caller sets.
- Which model. Argent reads the model from the request body and checks it against the approved list and access rules before anything leaves.
- Refuse or allow. A model nobody approved is refused at the gateway with a named reason, such as
llm.deny.model. - Sensitive data. The request is scanned, and secrets and personal data are redacted, recorded or blocked under your policy. If the scan cannot run, the request is refused, never passed as clean.
- Budget. The request is priced and the amount is held against the agent's budget, so parallel calls cannot overshoot it.
- Key. The gateway attaches the provider key from your vault at egress.
- Reply and record. Token usage is read from the reply, the cost is settled, and the signed record is written.
What the record shows
Every the provider call leaves one signed record, allowed or refused.
- One row per call: the agent and the person who owns it, the tenant, the model, the decision and the policy that made it, latency, and the cost, token and cache figures.
- Tamper-evident: each row is hash-chained to the one before and signed with an ed25519 key held in Vault Transit, so an edited or missing row shows.
- Real cost: cost comes from the usage block in the provider's own reply, priced from your price book in USD per million tokens.
- No unpriced spend: an agent under a budget that calls a model with no price is refused, so a new model cannot slip past a cap.
Conversations can be opened and replayed from the record. See Session Replay and One-Click Audit Evidence.
Related capabilities and goals
Where to go next.
- Capabilities: Model Control, Keyless Agents, Sensitive Data Redaction, AI Spend Caps.
- Goals: Model control and routing, Budget and token spend, Sovereign AI.
- Works with: OpenAI, OpenRouter, vLLM, LiteLLM.
- Everything else Argent connects to: All integrations.
Download files
- PDFArgent Model Control data sheetApproved models, Model Swap, model classes and failover. One page.
- PDFArgent Keyless Agents data sheetProvider keys stay in your vault; agents carry only their own Argent key. One page.
- PDFArgent Sensitive Data Redaction data sheetPersonal data and secrets found and redacted before a prompt leaves. One page.
Want this running on your own use cases?
All downloads