
Argent with DeepSeek
Decide where DeepSeek models may run. Argent can refuse direct calls to DeepSeek, swap them to an approved model, or govern DeepSeek models you host in Azure Foundry, with every decision signed.
What Argent does with DeepSeek
Many security teams want a say in whether agents send data to DeepSeek's own API. Argent gives you that say, per tenant, department, person or agent.
- DeepSeek is recognized: Argent knows the DeepSeek API,
api.deepseek.com, and DeepSeek models appear in the console's model picker. - Refuse it: an access rule denies DeepSeek for anyone you choose, before the prompt leaves. Tested live.
- Swap it away: a Model Swap rule sends a DeepSeek request to an approved model class instead, and the agent's code does not change. Tested live, with the request served by an approved Azure model.
- Run it where you choose: DeepSeek models deployed in Azure Foundry are governed and priced through your Azure OpenAI and Foundry endpoint.
- Watch first: in watch mode the call goes through and is flagged, so you see who uses DeepSeek before you decide.
How it connects
Agents point at Argent; Argent decides what happens to a DeepSeek request.
- Register each agent with an owner. It gets its own Argent key and a Connect tab with copy-paste setup.
- Point it at Argent with its gateway route as the base URL.
- Choose the outcome for DeepSeek models: deny them, or swap them to an approved class. To run DeepSeek under your rules, use a DeepSeek model deployed in your Azure OpenAI and Foundry endpoint.
- Watch, then enforce. See Watch Before You Enforce.
What you configure
Everything below is set once in the Argent console and applies to every agent that calls DeepSeek 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. |
| Model Swap | Model Swap picker | Runs an approved model in place of the one the agent asked for, including when a budget runs low, with no change to agent code. |
| Model classes | Policy > Model classes | A name such as fast stands for an ordered list of approved models, with failover on connection errors, 5xx, 429, timeouts and retired models. |
| 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.
What the record shows
Every DeepSeek 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 DeepSeek'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, Shadow AI Discovery, Sensitive Data Redaction, Watch Before You Enforce.
- Goals: Model control and routing, See all AI in your company, Sovereign AI.
- Works with: DeepSeek API, Azure OpenAI and Foundry, OpenRouter.
- 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