LLM Gateway

The Nexus LLM Gateway gives applications one endpoint for the language models your school has configured in Nexus. Requests use your Nexus identity, so model access and usage attribution stay in one place.

Use the gateway when you want an application, automation, or coding tool to use organization-approved models without storing a separate provider key.

The LLM Gateway is available with Nexus Enterprise. An administrator must configure at least one visible language model before it can serve requests.

What the gateway provides#

• An OpenAI-compatible Chat Completions endpoint.

• An OpenAI Responses endpoint.

• An Anthropic Messages endpoint and token-count endpoint.

• The models that your Nexus identity can access.

• Usage attribution through the existing Nexus usage views.

• The same model access controls and token limits that apply in Nexus.

The gateway does not replace your model-provider configuration. An administrator still configures providers and decides which models are visible in Language Models.

Before you begin#

You need all of the following:

• A Nexus administrator has configured a language model and made it visible.

• Your Nexus account has access to that model.

• A Personal Access Token (PAT) with the LLM Gateway scope.

Create a Personal Access Token from Settings > Accounts & Access. Choose Limited access and select LLM Gateway. Treat the token as a password. Nexus shows it only once.

Use a scoped PAT for an application or local development. It limits the token to gateway requests while preserving the model access of the user who created it.

Gateway address#

For a standard Nexus deployment, use:

https://your-onyx-domain.com/api/gateway/v1

Self-hosted deployments can expose the API at a different public path. Use the public API address for your deployment, followed by /gateway/v1.

Every request uses a Bearer token:

export ONYX_GATEWAY_URL="https://your-onyx-domain.com/api/gateway/v1"
export ONYX_GATEWAY_API_KEY="onyx_pat_..."

Find an available model#

The easiest way to find a model ID is in Settings > LLM Gateway. The section appears only when at least one model is visible and accessible to your account.

Open a provider, then copy the ID beside the model that you want to use. The copied value already has the required format:

<provider-id>/<model-name>

For example, 12/gpt-5-mini means:

• 12 is the Nexus ID for the configured provider.

• gpt-5-mini is the model name configured for that provider.

Use the copied value exactly as the model value in your client. Do not replace the provider ID with the provider name.

Use Settings to find a model ID for each client configuration.

OpenAI Chat Completions#

Point OpenAI-compatible clients at the gateway URL. This example uses the official OpenAI JavaScript SDK.

import OpenAI from "openai";

const client = new OpenAI({
apiKey: process.env.ONYX_GATEWAY_API_KEY,
baseURL: process.env.ONYX_GATEWAY_URL,
});

const completion = await client.chat.completions.create({
model: "12/gpt-5-mini",
messages: [{ role: "user", content: "Write a one-line release note." }],
});

console.log(completion.choices[0].message.content);

The same request with stream: true uses server-sent events.

OpenAI Responses#

The gateway also supports the OpenAI Responses API. Use the same base URL and model ID.

const response = await client.responses.create({
model: "12/gpt-5-mini",
input: "Summarize the purpose of this service in one sentence.",
});

console.log(response.output_text);

Gateway responses are stateless. Send the context that a later turn needs; do not rely on a previous response ID being stored by Nexus.

Anthropic Messages#

For Anthropic-compatible clients, send requests to the gateway's messages endpoint with the same Bearer token and model ID.

curl "$ONYX_GATEWAY_URL/messages" \
-H "Authorization: Bearer $ONYX_GATEWAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "18/claude-haiku-4-5",
  "max_tokens": 256,
  "messages": [
    {"role": "user", "content": "Reply with one friendly greeting."}
  ]
}'

To estimate the input tokens for an Anthropic Messages request, send the same request shape to POST /messages/count_tokens.

Use with coding agents#

Use the gateway with Claude Code or Codex to give coding-agent requests the same model access controls, usage attribution, and token limits as other gateway traffic.

Claude Code#

Set the gateway's parent endpoint as the Anthropic base URL, then use a Claude model ID from Settings:

export ANTHROPIC_BASE_URL="https://your-onyx-domain.com/api/gateway"
export ANTHROPIC_AUTH_TOKEN="$ONYX_GATEWAY_API_KEY"
export ANTHROPIC_MODEL="18/claude-haiku-4-5"
export ANTHROPIC_SMALL_FAST_MODEL="18/claude-haiku-4-5"

claude

Claude Code appends /v1/messages, which resolves to the gateway's Anthropic Messages endpoint. Use a model ID from your own Settings page. Provider IDs differ by deployment.

Codex#

Create a Codex profile at ~/.codex/onyx.config.toml:

model = "12/gpt-5-mini"
model_provider = "onyx_gateway"

[model_providers.onyx_gateway]
name = "Onyx Gateway"
base_url = "https://your-onyx-domain.com/api/gateway/v1"
wire_api = "responses"
env_key = "ONYX_GATEWAY_API_KEY"

Then export the PAT and start Codex with that profile:

export ONYX_GATEWAY_API_KEY="onyx_pat_..."
codex -p onyx

The configured model must be an OpenAI-compatible model ID from Settings.

OpenCode#

Add the gateway as an OpenAI-compatible provider in your project's opencode.json:

{
"$schema": "https://opencode.ai/config.json",
"model": "onyx_gateway/12/gpt-5-mini",
"provider": {
  "onyx_gateway": {
    "npm": "@ai-sdk/openai-compatible",
    "name": "Onyx Gateway",
    "options": {
      "baseURL": "https://your-onyx-domain.com/api/gateway/v1",
      "apiKey": "{env:ONYX_GATEWAY_API_KEY}"
    },
    "models": {
      "12/gpt-5-mini": {
        "name": "GPT-5 mini via Onyx"
      }
    }
  }
}
}

Export a PAT before starting OpenCode:

export ONYX_GATEWAY_API_KEY="onyx_pat_..."
opencode

The @ai-sdk/openai-compatible provider uses the gateway's Chat Completions endpoint. Replace the example model with one from your Gateway Settings.

Usage and limits#

Gateway requests use the calling user's Nexus permissions. If the user loses access to a model, the gateway no longer exposes or accepts that model for the user.

Administrators can review token use and estimated model cost in Admin Panel

Usage. They can also apply global, group, or user token limits there. Those limits apply before the gateway sends a generation request to a model provider.

Native passthrough#

Requests that resolve to an Anthropic provider or a true OpenAI model are proxied natively to the provider. Hosted and server tools, extended thinking, and fine-grained streaming pass through unchanged. Requests for other providers are translated through the OpenAI-compatible path.

Self-hosted administrators can turn passthrough off with these environment variables on the API server:

• ANTHROPIC_GATEWAY_PASSTHROUGH_ENABLED=false: send Anthropic-backed providers through the translation path.

• OPENAI_GATEWAY_PASSTHROUGH_ENABLED=false: send true-OpenAI models through the translation path.

Both default to on.

Common errors#

Next steps#

Configure language models#

Add providers and control which models are visible.

Create a Personal Access Token#

Create and manage the token used by your application.