ForgeCode with AI Gateway

ForgeCode is a terminal coding agent. It supports custom OpenAI-compatible providers, which you can point at AI Gateway for unified model access and spend monitoring.

Run the Vercel CLI setup command for ForgeCode:

npx vercel ai-gateway setup --agent forge

The command writes a gateway [[providers]] entry and [session] defaults into ~/.forge/.forge.toml. It stores the key in the sibling .credentials.json with 0600 permissions, which is the only key source Forge 2.13 and later read. Re-run it to refresh the defaults.

If you can't use the Vercel CLI, configure ForgeCode manually:

1. Create an API key

   Go to the AI Gateway section in the Vercel dashboard sidebar and click API keys to create a new API key.

2. Add the gateway provider

   Add a [[providers]] entry to ~/.forge/.forge.toml:

   ~/.forge/.forge.toml

   [[providers]]
   id = "vercel-ai-gateway"
   url = "https://ai-gateway.vercel.sh/coding-agent/v1/chat/completions"
   models = "https://ai-gateway.vercel.sh/coding-agent/v1/models"
   api_key_vars = "AI_GATEWAY_API_KEY"
   response_type = "OpenAI"
   auth_methods = ["api_key"]
    
   [session]
   provider_id = "vercel-ai-gateway"
   model_id = "openai/gpt-6-astra"

3. Store the key

   Forge 2.13 and later resolve keys only from ~/.forge/.credentials.json, not the environment. Add the key to the JSON array with mode 0600:

   ~/.forge/.credentials.json

   [
     {
       "provider_id": "vercel-ai-gateway",
       "auth_details": {
         "api_key": "your-ai-gateway-api-key"
       }
     }
   ]

   Terminal

   chmod 0600 ~/.forge/.credentials.json

   Older Forge releases read the key from AI_GATEWAY_API_KEY in the environment instead, which is why the provider also declares api_key_vars.

4. Start ForgeCode

   Terminal

   forge

   Switch models in-session with :config-model. The picker fills from the gateway's /models endpoint, so the full catalog is available.

View your usage, spend, and request activity in the AI Gateway section in the Vercel dashboard sidebar. See the observability documentation for more details.

• Browse the models catalog for available models
• Configure spend limits on your API key