LangChain collapses seven LangSmith meters into two units: LCU and LSU
LangSmith dropped per-run and uptime deployment billing for two normalized units: LangChain Compute Units at $1.50 and new Storage Units at $1.00. Seats hold at $39.
Per-service rate card: traces billed per 1k, $0.005 per deployment run plus uptime minutes, $0.05 per Fleet run, $1.50/LCU for Engine, and dollar-denominated per-second sandbox rates.
Two normalized units: 1 LCU = $1.50 (work and compute) and 1 LSU = $1.00 (traces and storage). Deployments are metered on resources consumed (0.045 LCU/vCPU-hr runtime compute, 0.177 LSU/vCPU-hr database compute) across Serverless and Dedicated sizes; Fleet is LCU-metered with 5 LCU (Developer) or 25 LCU (Plus) included monthly; traces cost 0.005 LSU each beyond the base allowance.
Proof of change
LangChain's pricing pages, as we captured them on two dates.
Showing the whole page as captured — scroll either panel, or open it at full size.
Both images are our own captures, taken on the dates shown. The pixels are unmodified — nothing is retouched, and where a region is highlighted the marker is drawn over the image, not into it. Open either capture to see it at full resolution.
LangChain restructured the whole LangSmith rate card in July 2026. Instead of publishing a separate meter per product, every paid service now converts into one of two normalized units: the LangChain Compute Unit (1 LCU = $1.50, for work done and compute — Engine, Fleet, deployment runtime, sandbox compute) and the newly introduced LangChain Storage Unit (1 LSU = $1.00, for traces, deployment databases and sandbox storage).
The clearest casualty is deployment pricing. The flat $0.005-per-deployment-run charge and the standby uptime meters that replaced per-node billing in January 2026 are both gone; deployments are now Serverless or Dedicated, sized Small / Medium / Large, and charged purely on resources consumed — runtime compute at 0.045 LCU/vCPU-hr, runtime memory at 0.006 LCU/GiB-hr, database compute at 0.177 LSU/vCPU-hr and database memory at 0.025 LSU/GiB-hr. Plus still includes one free deployment, now specified as Serverless (Small).
Fleet moved off per-run pricing entirely: it is metered in LCUs at a rate that varies by model tier (Fast, Pro, Max), with 5 LCU/mo included on Developer and 25 LCU/mo on Plus. On Developer the allowance is a hard stop — Fleet pauses new runs until the monthly reset or an upgrade. Sandbox rates were restated in the same units (0.0384 LCU/vCPU-hr compute, 0.0123 LCU/GiB-hr memory, 0.000123 LSU/GiB-hr storage, all billed per second), and Engine run consumption is now published as roughly 5–30 LCUs per run.
Plan prices did not move: Developer stays at $0 with a maximum of one seat and 5k base traces per month, Plus at $39/seat/mo with unlimited seats and 10k base traces, Enterprise custom. LangChain also shipped a LangSmith Usage Calculator on the pricing page, which lets buyers stack product modules and share a configured LCU/LSU estimate by link — a direct answer to the “seven meters, unknowable ceiling” objection the previous rate card created.
LangSmith replaces its per-service rate card with two normalized currencies: the LangChain Compute Unit (1 LCU = $1.50, for work and compute) and the new LangChain Storage Unit (1 LSU = $1.00, for traces and storage). Per-run deployment billing and uptime minutes are retired in favour of resource metering (0.045 LCU/vCPU-hr runtime compute, 0.177 LSU/vCPU-hr database compute) across Serverless and Dedicated deployments in Small/Medium/Large sizes; Fleet moves from per-run pricing to LCU metering with 5 LCU (Developer) or 25 LCU (Plus) included monthly; sandbox rates are restated in LCU/LSU. Seats hold at $0 / $39 / custom, and a LangSmith Usage Calculator lands on the pricing page.