BYOK

Bring your own key (BYOK) connects a provider account you already pay for to your workspace. Console stores the provider credential and gives each connection one gateway URL. Members and integrations call that URL with a Console key and never handle the provider secret.

curl -X POST "https://opencode.ai/inference/custom/conn_.../chat/completions" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{ "role": "user", "content": "Say hi" }]
  }'

Connect a provider

In the Console, open Providers and click Connect Provider.
Pick a provider from the catalog and paste its API key, or click Add Custom Provider for any other endpoint.
Copy the Console API URL from the provider page.

https://opencode.ai/inference/custom/<connection_id>

Catalog providers come with their models preconfigured. Custom providers need a few more fields:

Field	Description
Base URL	Where Console forwards requests, for example `https://api.deepseek.com/v1`.
API schema	Chat Completions, Responses API, Anthropic Compatible, or Google Generative AI.
Auth mode	Bearer, API key header, or Custom header, plus the credential to send.
Models	The model IDs members can request, with optional pricing used for usage tracking.

Authentication

Replace <token> with a service account key created in Console. Console swaps it for the connection’s credential before forwarding, so the provider secret stays in the workspace.

Authorization: Bearer <token>

Console also reads the key from x-api-key, api-key, or x-goog-api-key, so provider SDKs work when pointed at the Console API URL.

Endpoints

Append the provider’s API path to the Console API URL. Console forwards the request to the connection’s base URL and returns the provider response unchanged.

API schema	Path
Chat Completions	`/chat/completions`
Responses API	`/responses`
Anthropic Compatible	`/messages`
Google Generative AI	`/models/<model>:generateContent`

Send the model ID as it appears on the provider page. When a model has a different API ID upstream, Console rewrites it. Requests for models that are not enabled on the connection are rejected.

Chat Completions

curl -X POST "https://opencode.ai/inference/custom/conn_.../chat/completions" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{ "role": "user", "content": "Say hi" }]
  }'

Responses API

curl -X POST "https://opencode.ai/inference/custom/conn_.../responses" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "input": "Say hi"
  }'

Anthropic Compatible

max_tokens is required.

curl -X POST "https://opencode.ai/inference/custom/conn_.../messages" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": "Say hi" }]
  }'

Google Generative AI

The model and method are part of the path. Replace :generateContent with :streamGenerateContent to stream the response.

curl -X POST "https://opencode.ai/inference/custom/conn_.../models/gemini-3.1-pro:generateContent" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{ "parts": [{ "text": "Say hi" }] }]
  }'

Use in OpenCode

Members do not need the gateway URL. Connections appear as providers in OpenCode for everyone who connects to the workspace with /connect, and /models lists their enabled models.

/connect

Usage and limits

The provider bills you for the tokens. Console records every request and, using the pricing configured on the model, counts it toward workspace and member monthly limits.