> This page is for Workforce.

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.merge.dev/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.merge.dev/_mcp/server.

# Models

> The four decisions behind employee model access, what an employee's AI client needs to route through Gateway, and what a request passes through on the way to a provider.

Employees point their AI client at Gateway instead of the model provider, so every model request they make arrives somewhere you control. The Models section is where you decide what happens to it.

Four decisions. The first three live on tabs under [Models](https://wf-develop.merge.dev/models/routing) in the Workforce dashboard; spend has its own page under Manage.

| Decision                               | Where                                | Page                                                   |
| -------------------------------------- | ------------------------------------ | ------------------------------------------------------ |
| Which models employees can reach       | All models, Blocklist, Provider keys | [Model access](/merge-workforce/models/access)         |
| How requests route across those models | Routing policies                     | [Routing](/merge-workforce/models/routing)             |
| What gets scanned on the way through   | DLP, Security alerts                 | [Model guardrails](/merge-workforce/models/guardrails) |
| What it may cost                       | Budget                               | [Budget](/merge-workforce/models/budget)               |

A seventh tab, Advanced, holds the controls that apply to your whole organization at once: vendor regions, zero data retention, request tags, and model migrations. It is still gated, so those settings live in the Gateway console for now. See [Advanced](/merge-workforce/models/advanced).

## What an employee's client needs

Three values, and they are the same three in every AI client.

| Input      | Value                                                                                                                                                    |
| ---------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Base URL   | `https://api-gateway.merge.dev/v1/openai` for OpenAI-compatible clients, `https://api-gateway.merge.dev/v1/anthropic` for Claude Code and Claude Desktop |
| API key    | A Gateway key, minted per employee by the desktop client or issued per Group                                                                             |
| Model name | `provider/model`, such as `anthropic/claude-opus-5`, or `default_routing`                                                                                |

Prefer `default_routing`. Model choice then lives in your routing policy rather than in a config file on every laptop, and changing which model a team uses stops being a fleet-wide edit. A request that names a model still gets access checks, guardrails, and budget enforcement; it skips only the routing decision.

Sending an Anthropic client to the OpenAI base URL is the most common setup mistake. [Connect employee AI clients](/merge-workforce/rollout/employee-clients) covers the per-client values and how they reach a machine.

## What a request passes through

Order matters, because it determines which of your controls an employee can and cannot route around.

1. **Access.** Blocklist rules and your vendor restrictions drop the models and vendors your organization does not allow. This runs before routing, so no strategy change reaches a blocked model.
2. **Guardrails.** The prompt is screened for sensitive data and injection attempts, then redacted, blocked, or recorded according to your rules.
3. **Routing.** The Group's routing policy, or the organization default, picks a model from what is left and a vendor to serve it.
4. **Budget.** An exhausted budget refuses the request with a `402` before any provider is called, so a blocked request costs nothing.
5. **Response.** The completion is screened on the way back, and the whole request is written to [LLM calls](/merge-workforce/logs/gateway) with the model, tokens, routing outcome, and cost.

Employees see none of this unless something fires. A refusal comes back as an ordinary API error in whatever client they are using.

## Next steps

#### [Routing](/merge-workforce/models/routing)

Pick a strategy and attach it to a Group or to the whole organization

#### [Model access](/merge-workforce/models/access)

Set which vendors and models your organization allows, and block the rest

#### [Model guardrails](/merge-workforce/models/guardrails)

Screen prompts and completions for sensitive data and injection attempts

#### [Advanced](/merge-workforce/models/advanced)

Vendor regions, data retention, tags, and migrations