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

​
What costs credits

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.
get_query_run_results is free: the Explorer Units were charged when the run was queued. Poll as long as you need.
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.

​
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.
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.

​
Developer Units

Realtime tools call Allium’s Realtime APIs, 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 for the full per-endpoint table, and Realtime data 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 [email protected] to raise a limit.

​
Row limits

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

​
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. Skills work the same way: list_skills returns only the ones your organization can access.
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 [email protected] if it’s still missing.

API Credits

Developer Unit cost per Realtime endpoint

Usage & billing

Check your org’s consumption in the App

Compute profiles

How warehouse size affects Explorer Units

SQL & queries

The async run and results flow