Get your API key
tracelayer / docs DOCUMENTATION

L0

Start here.

Install the SDK, add one line, and send your first trace. The API reference and SDK methods follow.

POST /v1/traces

{
  "project":
    "prj_llm_support_bot",
  "name": "rag-agent",
  "spans": [ … ]
}

201 Created

L1

Install and send your first trace.

Install, one line to initialize, traces flow.

Python

install

pip install tracelayer

initialize

import tracelayer

tracelayer.init(api_key="tl_live_...")  # one line — your existing calls are now traced
import tracelayer

# one line — your existing
# calls are now traced
tracelayer.init(
  api_key="tl_live_...")

TypeScript

install

npm install tracelayer

initialize

import { init } from "tracelayer";

init({ apiKey: "tl_live_..." }); // one line — your existing calls are now traced
import { init }
  from "tracelayer";

// one line — your existing
// calls are now traced
init({
  apiKey: "tl_live_...",
});

L2

API reference.

Endpoints ▾
POST /v1/tracesSend a trace
GET /v1/traces/:idFetch a single trace by ID
GET /v1/tracesList and page through your traces
GET /v1/projectsList your projects
POST /v1/tracesSend a trace
GET /v1/traces/:idFetch a single trace by ID
GET /v1/tracesList and page through your traces
GET /v1/projectsList your projects

POST /v1/traces

Request

POST /v1/traces
Authorization: Bearer tl_live_...

{
  "project": "prj_llm_support_bot",
  "name": "rag-agent",
  "spans": [
    { "type": "prompt",     "latency_ms": 12,   "tokens": 214 },
    { "type": "retriever",  "latency_ms": 2870, "tokens": 0 },
    { "type": "model_call", "latency_ms": 2062, "tokens": 2646 },
    { "type": "tool",       "latency_ms": 96,   "tokens": 0 },
    { "type": "answer",     "latency_ms": 30,   "tokens": 0 }
  ]
}
POST /v1/traces
Authorization:
  Bearer tl_live_...

{
  "project":
    "prj_llm_support_bot",
  "name": "rag-agent",
  "spans": [
    {
      "type": "prompt",
      "latency_ms": 12,
      "tokens": 214
    },
    {
      "type": "retriever",
      "latency_ms": 2870,
      "tokens": 0
    },
    {
      "type": "model_call",
      "latency_ms": 2062,
      "tokens": 2646
    },
    {
      "type": "tool",
      "latency_ms": 96,
      "tokens": 0
    },
    {
      "type": "answer",
      "latency_ms": 30,
      "tokens": 0
    }
  ]
}

Response

201 Created

{
  "id": "tr_3f9a2b7c",
  "project": "prj_llm_support_bot",
  "name": "rag-agent",
  "total_latency_ms": 5070,
  "total_tokens": 2860,
  "total_cost_usd": 0.0205
}
201 Created

{
  "id": "tr_3f9a2b7c",
  "project":
    "prj_llm_support_bot",
  "name": "rag-agent",
  "total_latency_ms": 5070,
  "total_tokens": 2860,
  "total_cost_usd": 0.0205
}

This is the shape of the API. Full API reference — in progress.

L3

SDK methods.

The methods you'll reach for.

  • init(...)

    Start tracing. One line; wraps your existing calls.

  • trace(...)

    Wrap a specific block or function by hand.

  • span(...)

    Record a single step inside a trace by hand.

  • redact(...)

    Strip sensitive fields before a trace is sent.

Full method signatures — in progress.

L4

Get your API key