Free
Free
Pricing page states AgentCost is free and open source under MIT with no tiers, seat limits, or paywalls.
- Access
- Pricing page states AgentCost is free and open source under MIT with no tiers, seat limits, or paywalls.
Developer Tools · Vendor site 2026-10-04
AgentCost tracks LLM and agent spend across OpenAI, Anthropic, Gemini, LangChain, and thousands of models in real time. It ships as MIT-licensed open-source software with an optional free hosted cloud, budget guardrails, and a Python SDK you can self-host via Docker.
Engineering teams running LLM agents who need cost observability, budgets, and optimization hints without a proprietary lock-in.
Vendor pricing explicitly avoids paid tiers; cost control is via your own cloud provider bills rather than AgentCost subscriptions.
AgentCost instruments agent workloads to show which models drive spend, surfaces guardrails, and remains free to self-host or use on the vendor's hosted cloud.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| LLM cost tracking | Homepage title promises real-time tracking for OpenAI, Anthropic, Gemini, and LangChain costs. | Facts sourced | 2026-10-04 |
| MIT license | Pricing meta description says the product is free open-source observability under the MIT License. | Facts sourced | 2026-10-04 |
| Model coverage | Structured data mentions monitoring across 3,500+ models. | Facts sourced | 2026-10-04 |
Understand the total cost
Free
Free
Pricing page states AgentCost is free and open source under MIT with no tiers, seat limits, or paywalls.
Conductor runs parallel coding agents on Mac with optional Conductor Cloud sandboxes, multiplayer workspaces, mobile control, and an API. It orchestrates first-party Claude Code, Codex, Cursor, and OpenCode agents using your subscriptions and keys, with isolated microVMs for long-running cloud jobs.
Explore toolCloudanix is a CNAPP+ platform spanning code, cloud, access, and agentic security on one graph. It offers CSPM, CIEM, workload protection, just-in-time access, coding-agent guardrails, and LLM-native investigation across AWS, Azure, GCP, and Kubernetes with self-serve Pro SKUs and enterprise options.
Explore toolCerebrium is a serverless GPU platform for deploying real-time AI workloads such as voice agents, video models, and LLMs with sub-second cold starts and elastic scaling. Teams run Python apps on managed GPUs across multiple regions and pay for compute by the second rather than reserved capacity.
Explore toolThe practical questions
Site FAQ says setup takes under two minutes: create a free account, install the Python SDK, and add import plus init lines while existing LangChain code stays unchanged.
AgentCost tracks LLM and agent spend across OpenAI, Anthropic, Gemini, LangChain, and thousands of models in real time. It ships as MIT-licensed open-source software with an optional free hosted cloud, budget guardrails, and a Python SDK you can self-host via Docker.
Pricing page states AgentCost is free and open source under MIT with no tiers, seat limits, or paywalls.. This record lists ongoing free access; check the plan limits before starting.
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Hosted cloud provisions projects with API keys; Python SDK instrumentation is documented for sending usage events.. API access and subscription access may have different terms; consult the linked sources.
Vendor pricing explicitly avoids paid tiers; cost control is via your own cloud provider bills rather than AgentCost subscriptions.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Reviewed vendor source
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.