# 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.

## 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 ask | Your 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.

| Tool | What it does | Scope | Same through the REST API |
|---|---|---|---|
| `list_ai_models` | List the AI model ids this project can call. | `ai:inference` | `GET /v1/ai/models` |
| `create_chat_completion` | Generate a reply from an AI model. | `ai:inference` | `POST /v1/ai/chat/completions` |
| `get_costs` | Galon spend of this project this month. | `usage:read` | `GET /v1/costs` |
| `get_metering` | Measured quantities of this project. | `usage:read` | `GET /v1/metering` |
| `get_limits` | Spending limits, used and reserved amounts. | `usage:read` | `GET /v1/limits` |
| `get_pricing` | Public Galon prices of the open services. | none | MCP only |

## Limits, free tier and pricing

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

| Limit | Value |
|---|---|
| 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 request | **256** |
| Tools per request | **128** |
| Images per request | **8** |
| Size of one image | **5 MiB** |
| Request body | **2 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.

| Item | Price | Unit |
|---|---|---|
| `Meta-Llama-3_3-70B-Instruct` | 1.197625 USD | per million input tokens |
| `Meta-Llama-3_3-70B-Instruct` | 1.197625 USD | per million output tokens |
| `gpt-oss-120b` | 0.1485 USD | per million input tokens |
| `gpt-oss-120b` | 0.7425 USD | per million output tokens |
| `gpt-oss-20b` | 0.07425 USD | per million input tokens |
| `gpt-oss-20b` | 0.278438 USD | per million output tokens |
| `Qwen2.5-VL-72B-Instruct` | 1.626625 USD | per million input tokens |
| `Qwen2.5-VL-72B-Instruct` | 1.626625 USD | per million output tokens |
| `Qwen3.5-397B-A17B` | 1.0725 USD | per million input tokens |
| `Qwen3.5-397B-A17B` | 6.435 USD | per million output tokens |
| `Qwen3.5-9B` | 0.17875 USD | per million input tokens |
| `Qwen3.5-9B` | 0.268125 USD | per million output tokens |
| `Qwen3.6-27B` | 0.715 USD | per million input tokens |
| `Qwen3.6-27B` | 4.82625 USD | per million output tokens |
| `Qwen3.8-27B` | 0.7425 USD | per million input tokens |
| `Qwen3.8-27B` | 4.82625 USD | per million output tokens |
| `bge-m3` | 0.018563 USD | per million input tokens |
| `Qwen3-Embedding-8B` | 0.185625 USD | per 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

- [Full service documentation](/cloud/docs/services/ai)
- [Connect your AI](/cloud/docs/ai-assistants)
- [All capabilities](/cloud/docs/agents)
- [API reference](/cloud/docs/api)
