Quickstart

Create a gateway in the console, connect a provider, send a request, and open the first trace. Choose SaaS unless prompts must stay in your network.

SaaS — NeuralTrust hosts the data plane. Nothing to install.
Private (Hybrid) — you run the data plane; the SaaS console still manages it.

Choose Private for data residency, private networking, deterministic capacity, or a production SLA. See Installation.

Open Getting started

In the NeuralTrust console, open TrustGate → Getting started.

Add a gateway

If you do not have a gateway, Add new Gateway opens automatically. Otherwise, open the gateway selector and choose New Gateway. Enter a Name and choose SaaS.For a Private data plane, choose Private, then select Docker, Kubernetes, or Manual. Deploy using the generated instructions, enter one bootstrap Dataplane URL, and select Save and Finish. Then open Settings → Agent Gateway → General to set or verify the separate LLM URL and MCP URL.The generated Docker quick path exposes the LLM/proxy service only. Use Kubernetes or a full deployment when you need MCP.See Private deployment for infrastructure details.

Step 1 · Connect a provider

Choose a provider and enter its credentials. Select Test connection to verify them, then select Connect.

Step 2 · Send request

Choose one of the provider’s models, enter a question, and select Send request. The console sends the request through the selected gateway.

Step 3 · Traces

Review the first trace, including its status, model, latency, token count, trace ID, and response. Continue to Playground, Consumer, or Security from the next-step cards.

Call from your application

The request in Getting started uses an internal playground token. It does not create a reusable API key for your application.

For production traffic:

Open Consumers.
Select Consumer; the New Consumer panel opens. You can also open an existing consumer.
For a new consumer, select API Key under Authentication and copy the generated key when it is shown—it appears only once. For an existing consumer, manage credentials under Auth.
Open Connect and use a snippet under Connection details.

The provider credential remains in TrustGate. Keep the consumer API key secret and use placeholders in shared examples.

SaaS

Use the SaaS gateway URL from Connection details. Do not add X-AG-Gateway-Slug.

curl -X POST "https://<gateway-host>/<consumer-slug>/v1/chat/completions" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model>",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Private (Hybrid)

Use the configured LLM URL and include the gateway slug:

curl -X POST "<configured-llm-url>/<consumer-slug>/v1/chat/completions" \
  -H "X-AG-Gateway-Slug: <gateway-slug>" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<model>",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Clients that only support a base URL plus an API key (OpenAI- or Anthropic-compatible SDKs, Cursor, Claude Desktop-style setups) can send the same ag_… key as Authorization: Bearer ag_… or x-api-key: ag_… instead of X-AG-API-Key. See Auth. Embeddings use the same host, consumer slug, and key:

curl -X POST "https://<gateway-host>/<consumer-slug>/v1/embeddings" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-3-small",
    "input": ["Hello from TrustGate"]
  }'

Providers, routing, and Bedrock / Vertex limits: Embeddings. Images use the same host, consumer slug, and key:

curl -X POST "https://<gateway-host>/<consumer-slug>/v1/images/generations" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A minimal TrustGate logo",
    "n": 1,
    "size": "1024x1024"
  }'

Providers and multipart edits/variations: Images. Files use the same host, consumer slug, and key:

curl -X POST "https://<gateway-host>/<consumer-slug>/v1/files" \
  -H "X-AG-API-Key: <your-api-key>" \
  -F purpose=assistants \
  -F file=@notes.txt

Providers and list/get/content/delete: Files. Rerank (Cohere v2 body) and model discovery:

curl -X POST "https://<gateway-host>/<consumer-slug>/v1/rerank" \
  -H "X-AG-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "rerank-english-v3.0",
    "query": "What is TrustGate?",
    "documents": ["TrustGate is an LLM gateway"]
  }'

curl "https://<gateway-host>/<consumer-slug>/v1/models" \
  -H "X-AG-API-Key: <your-api-key>"

Rerank · Models.

Next steps

From Getting started What’s next, open Playground, Consumer, or Security (policies) — or continue below.

Endpoints

Every route a client can call through a consumer.

Observability

Traces, metrics, and where to inspect past traffic.

Consumers

Auth, routing strategies, policies, Connect snippets.

Policies

Rate limits, budgets, guardrails, tool governance.

Start here

Configure

Endpoints

Routing

Policies

MCP

Observability

Call from your application

SaaS

Private (Hybrid)

Next steps

Endpoints

Observability

Consumers

Policies

​Call from your application

​SaaS

​Private (Hybrid)

​Next steps

Endpoints

Observability

Consumers

Policies

Call from your application

SaaS

Private (Hybrid)

Next steps