Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tensorcost.com/llms.txt

Use this file to discover all available pages before exploring further.

TensorCost

The control plane for every dollar your company spends on AI. TensorCost is AI cost governance across self-hosted GPU fleets, managed-inference APIs (Bedrock, Azure OpenAI, Vertex, OpenAI, Anthropic), and the agent workloads that drive both. One pane of glass. Real attribution. Recommendations that pay for the platform.

Start here

Get started

Sign up, connect your first cloud account, see your first recommendation in 48 hours.

Install agents

One-click CFN, Terraform, or Helm. IMDSv2 auto-detect, HMAC auth, ≤15-minute onboarding.

Connect Bedrock

The lead managed-inference adapter. Routing, prompt cache, provisioned-throughput, runaway-loop alerts.

Coverage matrix

TensorCost is the only governance layer that spans all three sides of the modern AI bill.
Workload classExamplesWhat we attributeHow we ingest
GPU fleetsA100, H100, H200, B200; MIG slices; NVLink topologies; on-prem Slurm/Ray; EKS/GKE/AKSPer-instance, per-MIG-slice, per-namespace, per-teamUnified GPU agent (gRPC + HMAC)
Managed inferenceAmazon Bedrock, Azure OpenAI, Vertex AI, OpenAI API, Anthropic APIPer-model, per-application, per-team, per-userCUR 2.0, CloudWatch metrics, invocation logs (read-only IAM)
Agent workloadsLangGraph, CrewAI, in-house orchestratorsPer-agent, per-workflow, per-conversation; runaway-loop detectionSame data plane as managed inference

Three SKUs

GPU FinOps

The original product. Fleet rightsizing, MIG slicing, spot blending, RI/Savings Plan optimization.

AI Inference Cost Governance

Bedrock + Azure OpenAI + Vertex + OpenAI + Anthropic, with model routing and prompt-cache recommenders.

Agent Cost Observability

Per-agent, per-workflow attribution. Loop and retry-storm anomaly detection. PagerDuty + Slack hooks.

Explore

Architecture

15 backend services, 14 microfrontends, 21 packages. NestJS + gRPC + Postgres + Redis on Fargate.

API reference

REST gateway, JWT-auth, tenant-scoped, versioned at /v1/.

Real-time events

Tenant-scoped socket.io for live recommendations, alerts, and agent fleet state.

ML & anomaly detection

Burn-rate alerts, forecasts, and the four shipped Bedrock recommenders.

Observability

OpenTelemetry, structured logs, customer-side audit trails.

Configuration

RBAC, tag mapping, budget hierarchies, alert routes, feature flags.

Feature flags

LaunchDarkly + useFeature(). Quarterly stale-flag cleanup ritual.

Compliance & SOC 2

Type I targeting Q3 2026. RLS on 21+ tables. Trust portal in progress.

Built by Vaadh Labs

TensorCost is built and operated by Vaadh Labs. Reach the team at support@tensorcost.com or open an issue at github.com/vaadh-labs/tensorcost.