LLM Cost Tracker

Self-hosted LLM cost tracking for Rails.

Every call your app makes through RubyLLM, the official OpenAI and Anthropic SDKs, Gemini, or any OpenAI-compatible API gets logged: tokens, cost, latency, tags. Calls go app → provider direct. No proxy.

Not Langfuse, Helicone, or LiteLLM. No prompts, no traces, no replay. Spend attribution only.

Requires Ruby 3.4+, Rails 7.1+, PostgreSQL or MySQL.

Shown with RubyLLM; the flow is identical for the official OpenAI and Anthropic SDKs — swap the gem and the instrument name (see the cookbook).

# Gemfile
gem "llm_cost_tracker"
gem "ruby_llm"

bin/rails llm_cost_tracker:setup

Runs the install generator, drops a price snapshot, migrates the database, and verifies via llm_cost_tracker:doctor. Then enable the integration in the generated config/initializers/llm_cost_tracker.rb:

LlmCostTracker.configure do |config|
  config.default_tags = -> { { environment: Rails.env } }
  config.instrument :ruby_llm
end

Edit it in place to add tags, switch on async ingestion, etc.

Your RubyLLM calls stay unchanged — every chat, embedding, transcription, image, and moderation call now lands in the ledger. Tag them to attribute spend:

LlmCostTracker.with_tags(user_id: Current.user&.id, feature: "chat") do
  RubyLLM.chat.ask("Hello")
end

Mount the dashboard in config/routes.rb, behind your auth:

authenticate :admin do
  mount LlmCostTracker::Engine => "/llm-costs"
end

The engine ships without authentication on purpose.

• Calls. Provider, model, total tokens, total cost, latency, status.
• Line items. Per-component breakdown — text/audio/cached tokens, tool charges (web search, code execution, grounding, container sessions).
• Tags. Whatever attribution you pass — user, feature, tenant, env.
• Provider IDs. Response, project, API key, workspace — for downstream audits.
• Pricing snapshot. So historical numbers don't drift when prices change.

Streams capture when the provider emits final usage. OpenAI Faraday streams get stream_options: { include_usage: true } auto-injected so the final usage chunk lands in the ledger (opt out via config.auto_enable_stream_usage = false).

• No proxy. Direct calls only.
• No prompts. Token counts and metadata only.
• No traces, evals, or prompt management. Different product, different gem.
• Not multi-service. Built for a Rails monolith.

For batch jobs, internal gateways, or anything without an SDK/Faraday hook:

LlmCostTracker.track(
  provider: :anthropic,
  model: "claude-sonnet-4-6",
  tokens: { input_tokens: 1500, output_tokens: 320 },
  tags: { feature: "summarizer", user_id: current_user.id }
)

• Configuration
• Pricing
• Budgets
• Data model
• Querying
• Dashboard
• Streaming
• Cookbook
• Extending
• Operations
• Architecture
• EU AI Act record-keeping
• Upgrading
• Changelog

bundle install
bin/check

MIT — see LICENSE.txt.