PromptLayer website screenshot

PromptLayer

PromptLayer is a prompt engineering, prompt management, and LLM observability platform. Its REST API logs and tracks LLM requests, manages a versioned prompt registry with release labels, ingests OpenTelemetry-style spans and traces, and runs evaluations and datasets so teams can monitor, debug, and improve their LLM applications.

4 APIs 0 Features
AILLMPrompt EngineeringPrompt ManagementObservabilityEvaluation

APIs

PromptLayer Request Logging & Tracking API

Logs and tracks LLM requests independent of provider via log-request, associates prompt templates and input variables with a request (track-prompt), and attaches scores (track-s...

PromptLayer Prompt Registry & Templates API

Retrieves rendered or raw prompt templates by name or id with version and release-label resolution, publishes new prompt template versions, and manages release labels so prompts...

PromptLayer Evaluations & Datasets API

Creates, lists, runs, and scores evaluation reports against datasets, and manages evaluation datasets and their rows built from uploaded files or request history, enabling syste...

PromptLayer Spans & Traces API

Ingests OpenTelemetry-style spans in bulk and via an OTLP traces endpoint, retrieves and closes traces, and scopes all activity to PromptLayer workspaces for end-to-end observab...

Collections

Pricing Plans

Rate Limits

Promptlayer Rate Limits

6 limits

RATE LIMITS

FinOps

Resources

👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
Website
Website
🔗
Documentation
Documentation
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: PromptLayer API
  version: '1.0'
request:
  auth:
    type: apikey
    apikey:
      key: X-API-KEY
      value: '{{apiKey}}'
      in: header
items:
- info:
    name: Logging & Tracking
    type: folder
  items:
  - info:
      name: Log an LLM request
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/log-request
      body:
        type: json
        data: '{}'
    docs: Logs a provider-agnostic LLM request using the Prompt Blueprint format.
  - info:
      name: Track prompt for a request
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/rest/track-prompt
      body:
        type: json
        data: '{}'
    docs: Associates a prompt template and input variables with a logged request.
  - info:
      name: Track score for a request
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/rest/track-score
      body:
        type: json
        data: '{}'
    docs: Attaches a 0-100 score to a logged request.
  - info:
      name: Track metadata for a request
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/rest/track-metadata
      body:
        type: json
        data: '{}'
    docs: Attaches a custom metadata dictionary to a logged request.
- info:
    name: Prompt Registry
    type: folder
  items:
  - info:
      name: Get a prompt template
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/prompt-templates/{identifier}
      body:
        type: json
        data: '{}'
    docs: Retrieves a prompt template by name or id, resolving version or release label.
  - info:
      name: Publish a prompt template version
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/rest/prompt-templates
      body:
        type: json
        data: '{}'
    docs: Creates a new prompt template or version with optional release labels.
- info:
    name: Evaluations & Datasets
    type: folder
  items:
  - info:
      name: List evaluation reports
      type: http
    http:
      method: GET
      url: https://api.promptlayer.com/evaluations
    docs: Lists evaluation reports in the workspace.
  - info:
      name: Create an evaluation report
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/evaluations
      body:
        type: json
        data: '{}'
    docs: Creates a new evaluation report over a dataset.
  - info:
      name: Get an evaluation report
      type: http
    http:
      method: GET
      url: https://api.promptlayer.com/evaluations/{id}
    docs: Retrieves an evaluation report by id.
  - info:
      name: Run an evaluation report
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/evaluations/{id}/run
    docs: Executes an evaluation report.
  - info:
      name: Get an evaluation report score
      type: http
    http:
      method: GET
      url: https://api.promptlayer.com/evaluations/{id}/score
    docs: Retrieves the score of an evaluation report.
  - info:
      name: List datasets
      type: http
    http:
      method: GET
      url: https://api.promptlayer.com/datasets
    docs: Lists evaluation datasets in the workspace.
- info:
    name: Spans & Traces
    type: folder
  items:
  - info:
      name: Ingest spans in bulk
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/spans-bulk
      body:
        type: json
        data: '{}'
    docs: Atomically ingests a batch of OpenTelemetry-style spans.
  - info:
      name: Ingest OTLP traces
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/otlp/v1/traces
      body:
        type: json
        data: '{}'
    docs: OpenTelemetry Protocol (OTLP) HTTP endpoint for ingesting traces.
  - info:
      name: Get a trace
      type: http
    http:
      method: GET
      url: https://api.promptlayer.com/traces/{id}
    docs: Retrieves a trace by id.
  - info:
      name: Close a trace
      type: http
    http:
      method: POST
      url: https://api.promptlayer.com/traces/{id}/close
    docs: Closes an open trace so no further spans can be appended.