How to build Helicone dashboards in Metabase

Helicone is an open-source LLM observability proxy that logs every request with token counts, cost, latency, and cache performance. Metabase is where you turn that LLM telemetry into shared, trustworthy dashboards. This guide covers two complementary paths: a lightweight MCP + CLI route that pulls live data with the Helicone MCP server and loads a CSV into Metabase with the Metabase CLI, and a durable pipeline route that syncs Helicone rollups into a database so you can build dashboards anyone can read.

How do you connect Helicone to Metabase?

Most teams combine both routes: use quick exports and CLI uploads for a fast first pass, then move recurring cost and quality reporting to a warehouse-backed model.

What can you analyze from Helicone data in Metabase?

Each view below is built from request logs, plus the sessions, users, and cache hits your sync exposes:

• LLM spend by model and application
• Cost per user and per feature
• Cache hit rate and savings
• Latency and error trends
• Token usage growth

Which Helicone dashboards should you build in Metabase?

How do you use the Helicone MCP server with the Metabase CLI?

Pair the Helicone MCP server with the Metabase CLI for fast, hands-on analysis. MCP is useful for scoped lookups and summarized exports; the Metabase CLI's upload command loads CSV data into Metabase and creates a ready-to-query table and model.

Example workflow

• Ask the MCP server for daily usage and spend rollups by model and application.
• Export the result as CSV, keeping stable IDs, apps, models, environments, token counts, costs, and timestamps.
• Run mb upload csv to load it into Metabase as a table and model, then build questions and dashboards on top.

Be honest about the limits

• MCP lookups are excellent for exploration, not scheduled reporting.
• A CSV upload is a snapshot; refresh it with mb upload replace or move to the pipeline for real history.
• Daily usage rollups are required for spend trends — a single export is a snapshot, and some usage APIs only return a trailing window.
• mb upload csv needs an uploads database configured under Admin → Settings → Uploads.

How do you set up Helicone MCP and the Metabase CLI?

{
  "mcpServers": {
    "helicone": {
      "command": "npx",
      "args": ["-y", "@helicone/mcp@latest"],
      "env": {
        "HELICONE_API_KEY": "sk-helicone-..."
      }
    }
  }
}

Early-stage but official: two read tools, query_requests (defaults to 100 results, request/response bodies off unless asked) and query_sessions (needs explicit start and end timestamps). US and EU regions are both supported.

# Install the Metabase CLI
npm install -g @metabase/cli

# Log in (opens your browser; requires Metabase v62+)
mb auth login --url https://your-metabase.example.com

# Load a request-logs export — creates a table AND a model
mb upload csv --file helicone-request-logs.csv --collection root

# Refresh that same table later from a new export
mb upload replace <table-id> --file helicone-request-logs.csv

Can you generate a Helicone dashboard with AI?

Yes. Use the prompt below with any assistant that can run the Helicone MCP server and the Metabase CLI. It works end to end: if Helicone tables already exist in Metabase it analyzes those; otherwise it pulls scoped, summarized data, loads it with mb upload csv, then builds the dashboard and caveats any metric that needs missing history.

Create a polished Metabase dashboard for Helicone llm cost analytics.
Work end to end: get the data into Metabase if it isn't there yet, then build.

Goal: Help engineering, product, and finance partners understand spend by model and app, unit costs, cost per user, cache savings, and budget tracking from Helicone data.

Step 1 — Find or load the data:
- First, check what already exists in Metabase (search for helicone tables and
  models). If durable Helicone data is already present — synced from a warehouse
  or uploaded earlier — use it and skip to Step 2.
- If nothing is there, pull a scoped, summarized export with the Helicone MCP server:
  request logs, plus sessions, users, cache hits.
  Prefer aggregated or rollup views over raw traces. Write each result to a CSV,
  then load it with the Metabase CLI — run "mb upload csv --file <export>.csv" so
  each upload creates a table and a ready-to-query model. Use "mb upload replace
  <table-id> --file <export>.csv" to refresh an existing table instead of creating
  duplicates.

Step 2 — Inspect before querying:
Do not assume exact table or column names. Inspect available fields, apps, models,
environments, timestamps, and whether rollups or history exist before creating
duration or trend cards.

Important:
- Build on whatever data is present; don't claim Metabase connects natively to
  Helicone — it reads a database or CLI-uploaded tables.
- Never load raw prompt/response payloads into Metabase; use rollups, trace
  summaries, and experiment- or score-grain data.
- Only compute latency percentiles and durations when the required timestamps
  or pre-aggregated percentile fields exist.
- Exclude test, staging, and playground traffic from headline cost and quality
  cards, and segment by environment where the field exists.
- A single CSV is a point-in-time snapshot: only build trend cards if there is a
  usable date column or multiple periods have been uploaded.

Dashboard title: Helicone LLM Cost Overview

Sections:
1. Executive summary: Spend last 30 days; MoM growth; Cost per request;
   Cost per active user; Cache savings.
2. Spend: Daily/weekly spend by model, app, and team.
3. Unit costs: Cost per 1M tokens by model; prompt vs. completion ratio;
   cache hit rate.
4. Users and features: Cost per active user; cost by feature; top tenants.
5. Hygiene: Spend by API key; failed-request spend; deprecated-model traffic.

Filters: Date range, App, Model, Environment, User or team, Status.

Output: Build the dashboard if you have permission; otherwise provide the exact
questions, SQL, model definitions, and layout. Include caveats for any metric
that cannot be calculated from the available data.

How do you sync Helicone data into a database or warehouse?

For dashboards that need history and reliability, land Helicone rollups and metadata in a database first, then connect Metabase to that database.

Connector options

• Direct database or export pipeline — use the vendor's storage or export path when it reaches a database you control.
• Custom pipeline — use the Helicone REST API for control over rollup grain, fields, and refresh cadence.
• MCP + CSV — use this for quick exploration and one-off slices.

Self-hosted Helicone stores request logs in ClickHouse — point Metabase at it directly for full-fidelity cost analysis. On Helicone Cloud, script the REST API into daily rollups per model and app; no managed Airbyte or Fivetran connector exists.

Notes

• Decide the rollup grain first (daily per app/model is the workhorse) — it drives warehouse cost and every trend card.
• Land raw entity tables first, then build clean Metabase models on top.
• Normalize app, model, provider, window-start, token-count, and cost-USD fields.
• Strip or hash prompt/response payloads and user identifiers before they reach the warehouse — cost and quality analytics don't need them.

How should you model Helicone data in Metabase?

Core tables

Modeling advice

• Build a clean llm_request_rollups model with common columns across tools, so multi-source dashboards don't fork definitions.
• Separate entity tables (apps, models, datasets, prompts) from time-series rollups and trace- or score-grain tables.
• Exclude test, staging, and playground traffic from headline cost and quality metrics; keep environment as an explicit column.
• Use stable IDs for app, model, and experiment joins; display names and model aliases change.

Which Helicone metrics should you track in Metabase?

What SQL powers Helicone dashboards in Metabase?

These assume a cleaned analytical model in a warehouse (PostgreSQL dialect). Adjust table and column names to match your pipeline.

SELECT
  date_trunc('month', window_start) AS month,
  model,
  ROUND(SUM(cost_usd), 2) AS cost_usd,
  SUM(prompt_tokens + completion_tokens) AS total_tokens
FROM llm_request_rollups
GROUP BY 1, model
ORDER BY 1, cost_usd DESC;

SELECT
  model,
  ROUND(SUM(cost_usd), 2) AS cost_usd,
  SUM(prompt_tokens + completion_tokens) AS total_tokens,
  ROUND(
    1e6 * SUM(cost_usd)
    / NULLIF(SUM(prompt_tokens + completion_tokens), 0), 2
  ) AS cost_per_1m_tokens
FROM llm_request_rollups
WHERE window_start >= CURRENT_DATE - INTERVAL '30 days'
GROUP BY model
ORDER BY cost_usd DESC;

SELECT
  date_trunc('month', window_start) AS month,
  ROUND(SUM(cost_usd), 2) AS cost_usd,
  COUNT(DISTINCT user_id) AS active_users,
  ROUND(
    SUM(cost_usd) / NULLIF(COUNT(DISTINCT user_id), 0), 4
  ) AS cost_per_active_user
FROM llm_user_rollups
GROUP BY 1
ORDER BY 1;

What are common mistakes when analyzing Helicone in Metabase?

Related

Related analytics

Related dashboards

Related integrations

FAQ