AI
Add AI features without a surprise bill
Prepaid balance, reservation before each call and caps per key: the spend stops where you set it.
Get started
Three steps
- Top up a prepaid balanceNothing is billed after the fact
- Call chat completionsEach request is reserved before the model runs
- Set a cap per keyLower than the project limit if you want; spend stops there
- Works through MCP, CLI or API
- Prepaid, never billed after
- Your cap, alert at 75%
curl -X POST https://api.galon.ai/v1/ai/chat/completions \ -H "Authorization: Bearer gln_test_••••" \ -H "Content-Type: application/json" \ -d '{"model": "{model}", "messages": [{"role": "user", "content": "Write a two-line menu description for an espresso."}]}' # the models served, with their prices curl https://api.galon.ai/v1/ai/models \ -H "Authorization: Bearer gln_test_••••"
# your coding agent, Galon's MCP server connected > Which models can I call, and what do they cost per million tokens? # the agent calls list_ai_models, get_pricing