LangSmith
The workspace's project list, then each project's LLM runs inside the window with twelve named fields: timing, status, tokens, cost and the metadata that names the model. Never an input, never an output, never a prompt.
Access
- Kind
- A read-only key you paste
- What to give
- API key
- Why that one
- A LangSmith API key for the workspace. Valistry lists projects and reads the LLM runs' tokens and cost, with an explicit field list that carries no input and no output.
What it attributes on its own
- From the source
- day · project · model as LangSmith priced it · runs · input and output tokens · what LangSmith costed them at · runs that errored
- Needs a rule or a trace
- the provider's invoice — LangSmith computes a cost, it does not bill you · team, workflow and agent unless a rule maps the project · outcome — feedback scores are a later slice
The addresses it calls
- https://api.smith.langchain.com
Only these. A call anywhere else is refused before it leaves, and every call is logged.
Connecting it
- Create an API key. Settings → API Keys → Create API Key. A service key reads every project in the workspace; a personal key reads what you can see. Open ↗
- Confirm the host. US cloud, EU cloud, or the address of your own deployment.
- Paste both and click Test and connect. Valistry lists projects, reads the last seven days of LLM runs a page at a time, reports what it found, then fills thirty.
LangSmith holds a cost; the provider bills it. Connecting both LangSmith and a provider it traces counts the same call twice — connect one. LangSmith is the better of the two when you need the project on the row; the provider is better when you need the invoice.