Tidal Telemetry
Tidal Telemetry is the live cost view in the Tidal suite, next to Tidal Audit and Tidal Gateway. It is a live trial, it is how you and we see the same numbers, and it is included in the engagement.
What it is
Live cost by provider, model, feature, team and workflow, and the evidence behind the monthly savings statement. Install the SDK, call the init function, and every model call your application makes starts arriving as a trace: model, tokens in and out, an estimated cost per call, latency, errors.
- Instrumentation for common AI libraries. The Python SDK supports OpenAI, Anthropic and popular agent frameworks. Other languages can send standard OTLP traces.
- Plain OpenTelemetry, so the SDK is optional. Ingest is OTLP over HTTPS with a bearer token. Point any OpenTelemetry exporter at your project endpoint and it behaves identically. The SDK is a thin wrapper over the Apache-licensed OpenLIT SDK.
- Isolated per-project storage. Each project gets its own database and its own ingest key, enforced at the storage layer rather than by a filter in a query.
- A built-in MCP server. Agents can verify the setup, send a test trace and pull usage reports directly, which is a faster loop than reading a dashboard.
What it costs
Nothing on top of the engagement. Tidal Telemetry operations are included in the flat 20% of verified savings, with no licence fee. It is a live trial today.
How it relates to the engagement
Telemetry shows what your LLMs spend. The FinOps LLM engagement is the work that reduces it, priced on verified savings.
- Tidal Audit is the free, read-only review of your invoices and usage logs, run by our team. Audits run against provider billing data - the OpenAI Costs endpoint, the Bedrock CUR, the Vertex BigQuery export.
- Tidal Gateway is the LiteLLM gateway we deploy and operate in your cloud, where the changes ship.
- Tidal Telemetry measures what the gateway saves and is the evidence behind the monthly statement. It is included in the 20%.
A cost consultant who also owns the meter has an obvious problem, so every baseline behind every fee comes from raw provider invoices, and Telemetry is used to reconcile against them.
Existing users can sign in to Tidal. To try it on your own traffic, request access. The setup docs cover Python and plain OpenTelemetry. If you want someone to read your invoice and tell you where the money went, request the free audit.
FAQ
What is Tidal Telemetry?
Live LLM cost by provider, model, feature, team and workflow, from the same team as FinOps LLM. Every model call arrives as a trace with model, token counts, estimated cost, latency and errors attached. It is the evidence behind the monthly savings statement.
Is Tidal Telemetry part of the FinOps LLM engagement?
Yes. Tidal Telemetry measures the savings from Tidal Gateway and is included in the flat 20%. The baseline and the monthly reconciliation still come from your raw provider invoices, not from our own dashboard.
What does Tidal Telemetry cost?
Nothing on top of the engagement. Tidal Telemetry operations are included in the flat 20% of verified savings. It is a live trial at telemetry.llmcfo.com.
Do I have to install your SDK to send data?
No. Ingest is plain OTLP over HTTPS with a bearer token, so any OpenTelemetry exporter can point at your project endpoint directly. The SDK is a convenience wrapper over the Apache-licensed OpenLIT SDK, not a requirement.