Humanloop LLM Platform API

aid: humanloop:llm-platform
name: Humanloop LLM Platform API
description: The Humanloop REST API and SDKs covered prompts, tools, datasets, evaluations, evaluators,
  and logs for LLM applications. Developers called prompt endpoints from production to capture logs, ran
  evaluations against datasets, and managed versioned prompt configurations. The platform is being sunset
  following the team's acquisition by Anthropic in 2025.
humanURL: https://humanloop.com/docs
baseURL: https://api.humanloop.com/v5
tags:
- Prompts
- Tools
- Datasets
- Evaluations
- Evaluators
- Logs
- Files
properties:
- type: Documentation
  url: https://humanloop.com/docs
- type: APIReference
  url: https://humanloop.com/docs/api-reference
- type: SDK
  url: https://github.com/humanloop/humanloop-python
- type: SDK
  url: https://github.com/humanloop/humanloop-typescript
- type: GitHubOrganization
  url: https://github.com/humanloop
- type: MigrationGuide
  url: https://humanloop.com/docs/guides/migrating-from-humanloop
- type: SunsetAnnouncement
  url: https://humanloop.com
features:
- name: Prompt Management
  description: Versioned, collaborative prompt editor with structured variables and side-by-side comparisons.
- name: Evaluations
  description: Run dataset-driven evaluations with LLM-as-judge and code-based evaluators.
- name: Datasets
  description: Manage curated examples and production samples for evaluations and fine-tuning.
- name: Logs and Observability
  description: Capture every LLM call with inputs, outputs, costs, and latencies for production debugging.
- name: Online Evaluators
  description: Score live traffic in production with custom evaluators.
- name: Tools and Functions
  description: Define reusable tools and function specs that prompts can call.
- name: Multi-Provider Routing
  description: Use OpenAI, Anthropic, Google, and other providers through a single API surface.
- name: Python and TypeScript SDKs
  description: First-class SDKs for invoking prompts and logging from application code.
useCases:
- name: Production Prompt Iteration
  description: Update prompts in Humanloop without redeploying application code.
- name: LLM Evaluation
  description: Score prompts and models against curated datasets before shipping.
- name: Production Monitoring
  description: Log every LLM call and trace quality regressions in production.
- name: Cross-Functional Collaboration
  description: Let PMs, designers, and engineers collaborate on prompts in one workbench.
integrations:
- name: OpenAI
- name: Anthropic
- name: Google
- name: Cohere
- name: AWS Bedrock
- name: Azure OpenAI
- name: LangChain
- name: LlamaIndex
authentication:
- type: API Key
  description: Workspace API keys passed via the `X-API-KEY` header authenticated REST and SDK calls.