> ## Documentation Index
> Fetch the complete documentation index at: https://docs.allium.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Billing & limits

> Which MCP tools consume credits, how much data comes back, and why your tool list may be shorter than the docs.

MCP tool calls bill against the same Explorer Unit and Developer Unit pools as the rest of Allium.

## What costs credits

| Tool group | Cost |
| :- | :- |
| `run_sql_query`, `create_explorer_query`, `run_explorer_query` | **Explorer Units**, based on the warehouse and how long the query runs |
| Realtime and Hyperliquid tools | **Developer Units**, a fixed cost per endpoint |
| `update_explorer_query`, `delete_explorer_query` | Metered as tool calls; no query compute |
| Everything else | Free |

**Free tools:** `search_schemas`, `search_docs`, `browse_docs`, `search_terminal`, `get_terminal_results`, `list_skills`, `get_skill`, `list_compute_profiles`, `get_query_run_results`, `get_explorer_query`, `list_explorer_queries`, `get_realtime_supported_chains`, all dashboard, visual, and sharing tools.

<Info>
  `get_query_run_results` is free: the Explorer Units were charged when the run was queued. Poll as long as you need.
</Info>

<Note>
  **Two different meters.** Realtime and Hyperliquid tools charge Developer Units per endpoint. Every metered MCP tool call is also checked against your **Explorer Unit** allowance before it runs, so a realtime call can be refused when that allowance is exhausted. Check both balances if you hit an unexpected limit error.
</Note>

### Explorer Units

Query cost scales with the compute profile and how long the query runs. `get_query_run_results` returns the run's exact Explorer Unit cost.

<Warning>
  Running SQL with `run_sql_query` and then saving the same SQL with `create_explorer_query` bills the compute twice. If the result might be reused, use `create_explorer_query(run_on_creation=true)` from the start.
</Warning>

### Developer Units

Realtime tools call Allium's [Realtime APIs](/api/developer/overview), so they consume between 20 and 60 Developer Units per call depending on the endpoint. Batched calls multiply that by the number of inputs: a `get_realtime_token_latest_price` call with 10 payloads costs 10x the single-call rate.

See [API Credits](/api/developer/compute-units) for the full per-endpoint table, and [Realtime data](/ai/mcp/tools-reference/realtime#every-tool-names-its-own-docs) for the tool-to-endpoint mapping.

### When you run out

If your organization is over its credit cap or overage limit, billed tools fail with an error explaining the limit. Free tools keep working. Contact [support@allium.so](mailto:support@allium.so) to raise a limit.

## Row limits

SQL results pass two caps: one on the query run, one on what the tool hands back.

| Cap | Value | Applies to |
| :- | :- | :- |
| Query result rows | **1,000** | A `run_sql_query` run |
| Query result rows | **10,000** by default, configurable per organization | A saved-query run (`create_explorer_query` / `run_explorer_query`) |
| Tool response rows | **50** by default | What `get_query_run_results` hands your agent |

Raise the last one with `row_limit`, or pass `null` or `0` for no tool-side truncation. The default is small so a wide result doesn't fill your agent's context window.

<Tip>
  If you need more than 1,000 rows, aggregate in SQL. A `GROUP BY` on a large blockchain table is cheaper than moving rows into your agent. When you need the rows themselves, save the query with `create_explorer_query`, which has the higher cap.
</Tip>

Other limits:

| Limit | Value |
| :- | :- |
| `get_query_run_results` poll window | 180 seconds max per call |
| `search_schemas` / `search_terminal` hits | 20 max, 5 by default |
| `get_terminal_results` rows | Set by `max_rows` |

## Tool visibility

Some capabilities are enabled per organization. A tool your organization doesn't have never reaches your agent, so the tools your client shows can be fewer than the [full tool list](/ai/mcp/tools-reference/overview#full-tool-list). Skills work the same way: `list_skills` returns only the ones your organization can access.

<Note>
  Visibility fails closed: if authentication fails, gated tools are hidden. If you expect a tool and don't see it, check that your API key is valid. Contact [support@allium.so](mailto:support@allium.so) if it's still missing.
</Note>

## Related resources

<CardGroup cols={2}>
  <Card title="API Credits" icon="bolt" href="/api/developer/compute-units">
    Developer Unit cost per Realtime endpoint
  </Card>

  <Card title="Usage & billing" icon="receipt" href="/app/organization-management/usage-and-billing">
    Check your org's consumption in the App
  </Card>

  <Card title="Compute profiles" icon="gauge-high" href="/app/query-management/compute-profiles">
    How warehouse size affects Explorer Units
  </Card>

  <Card title="SQL & queries" icon="database" href="/ai/mcp/tools-reference/sql-and-queries">
    The async run and results flow
  </Card>
</CardGroup>