Galon Cloud
Galon Cloud

AI models with your AI agent

Your agent calls AI models through Galon, paid per token from the project balance, and reads what the project spends.

Markdown · API reference · OpenAPI

What your agent can do

  • List the models this project can call.
  • Generate a reply from a model, with the amount charged in the answer.
  • Read this month's spend, the measured usage and the spending limits.

Ask your agent

Paste a request like these in your AI once it is connected. It calls the tools in this order.

You askYour agent calls
“Try a Galon model on this prompt and tell me what it cost.”list_ai_models → create_chat_completion
“How much has this project spent on Galon this month?”get_costs
“Why was my last request refused?”get_limits

Tools and routes

Every tool is a call to the REST route next to it, with the same permissions, limits and idempotency. tools/list shows only the tools your connection can call.

ToolWhat it doesScopeSame through the REST API
list_ai_modelsList the AI model ids this project can call.ai:inferenceGET /v1/ai/models
create_chat_completionGenerate a reply from an AI model.ai:inferencePOST /v1/ai/chat/completions
get_costsGalon spend of this project this month.usage:readGET /v1/costs
get_meteringMeasured quantities of this project.usage:readGET /v1/metering
get_limitsSpending limits, used and reserved amounts.usage:readGET /v1/limits
get_pricingPublic Galon prices of the open services.noneMCP only

Limits, free tier and pricing

Read from the platform code each time this page is served.

LimitValue
Requests per project and day (default quota)10,000
Requests per project and month (default quota)100,000
Requests per key and minute (sliding window)60
Tokens per key and minute (input bound + max output, sliding window)200,000
Default spending cap of a key per month (adjustable in the console)$5.00
Input per request (messages, default)64 KiB
Output tokens per request (Galon aliases)8,192
Messages per request256
Tools per request128
Images per request8
Size of one image5 MiB
Request body2 MiB

Usage prices, in US dollars, read from the price grid served by the platform each time this page is served. Paid from the prepaid balance.

ItemPriceUnit
Meta-Llama-3_3-70B-Instruct1.197625 USDper million input tokens
Meta-Llama-3_3-70B-Instruct1.197625 USDper million output tokens
gpt-oss-120b0.1485 USDper million input tokens
gpt-oss-120b0.7425 USDper million output tokens
gpt-oss-20b0.07425 USDper million input tokens
gpt-oss-20b0.278438 USDper million output tokens
Qwen2.5-VL-72B-Instruct1.626625 USDper million input tokens
Qwen2.5-VL-72B-Instruct1.626625 USDper million output tokens
Qwen3.5-397B-A17B1.0725 USDper million input tokens
Qwen3.5-397B-A17B6.435 USDper million output tokens
Qwen3.5-9B0.17875 USDper million input tokens
Qwen3.5-9B0.268125 USDper million output tokens
Qwen3.6-27B0.715 USDper million input tokens
Qwen3.6-27B4.82625 USDper million output tokens
Qwen3.8-27B0.7425 USDper million input tokens
Qwen3.8-27B4.82625 USDper million output tokens
bge-m30.018563 USDper million input tokens
Qwen3-Embedding-8B0.185625 USDper million input tokens

There is no free AI usage. Requests are paid per token from the prepaid balance, in US dollars.

Your agent reads the current prices with get_pricing and the spending limits with get_limits.

Good to know

  • Each request is billed per token to the project balance; the spending cap of the connection applies.
  • In your app, call the same route from your server with an API key read from the environment: any client of the Chat Completions standard works.

Next