Keywords AI logo

Keywords AI

Keywords AI is an LLM observability and gateway platform. It exposes an OpenAI-compatible proxy (chat completions across 250+ models) plus REST APIs for request logging, prompt management, threads, evaluations, and traces - all under a single Bearer-authenticated API at https://api.keywordsai.co/api. (The company is rebranding to Respan; the keywordsai.co host and API remain active.)

6 APIs 0 Features
AILLMObservabilityGatewayMonitoring

APIs

Keywords AI LLM Proxy (Chat Completions)

OpenAI-compatible chat completions proxy that routes requests to 250+ LLMs through one unified endpoint, with streaming (SSE), tool calling, structured outputs, fallbacks, load ...

Keywords AI Logging API

Asynchronous request-logging endpoint for ingesting LLM call telemetry (model, prompt/completion messages, tokens, cost, latency, customer identifier, metadata) when calls are n...

Keywords AI Prompts API

Manage prompts and prompt versions outside of application code - create, list, retrieve, update, and delete prompts; create, commit, and deploy versions with templated messages,...

Keywords AI Threads API

Query multi-turn conversation threads grouped from logged LLM calls, with filtering and pagination for reconstructing end-user sessions.

Keywords AI Evaluations API

Create and run evaluators to score LLM outputs - manage evaluator definitions and execute them against logs and datasets to measure quality, correctness, and safety.

Keywords AI Traces API

List, retrieve, and delete distributed traces (OpenTelemetry-aligned spans) capturing agent and multi-step LLM workflows for observability and debugging.

Event Specifications

Keywords AI Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of Keywords AI's **chat completion streaming** surface on the OpenAI-compatible gateway. Keywords AI does not publish a WebSocket API. The only asynchro...

ASYNCAPI

Resources

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

Sources

Raw ↑
aid: keywordsai
url: https://raw.githubusercontent.com/api-evangelist/keywordsai/refs/heads/main/apis.yml
name: Keywords AI
kind: company
description: Keywords AI is an LLM observability and gateway platform. It exposes an
  OpenAI-compatible proxy (chat completions across 250+ models) plus REST APIs for
  request logging, prompt management, threads, evaluations, and traces - all under a
  single Bearer-authenticated API at https://api.keywordsai.co/api. (The company is
  rebranding to Respan; the keywordsai.co host and API remain active.)
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- LLM
- Observability
- Gateway
- Monitoring
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: keywordsai:llm-proxy-chat-completions
  name: Keywords AI LLM Proxy (Chat Completions)
  tags:
  - Chat
  - Completions
  - Gateway
  - LLM
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.keywordsai.co/api-endpoints/integration/chat-completions
  baseURL: https://api.keywordsai.co/api
  properties:
  - url: https://docs.keywordsai.co/api-endpoints/integration/chat-completions
    type: Documentation
  - url: https://docs.keywordsai.co/api-endpoints/integration/chat-completions
    type: APIReference
  - url: openapi/keywordsai-openapi.yml
    type: OpenAPI
  - url: asyncapi/keywordsai-asyncapi.yml
    type: AsyncAPI
  - url: collections/keywordsai.postman_collection.json
    type: PostmanCollection
  description: OpenAI-compatible chat completions proxy that routes requests to 250+
    LLMs through one unified endpoint, with streaming (SSE), tool calling, structured
    outputs, fallbacks, load balancing, caching, and automatic request logging.
- aid: keywordsai:logging
  name: Keywords AI Logging API
  tags:
  - Logging
  - Observability
  - Request Logs
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.keywordsai.co/api-endpoints/async-endpoints/request-logging-endpoint
  baseURL: https://api.keywordsai.co/api
  properties:
  - url: https://docs.keywordsai.co/api-endpoints/async-endpoints/request-logging-endpoint
    type: Documentation
  - url: openapi/keywordsai-openapi.yml
    type: OpenAPI
  - url: collections/keywordsai.postman_collection.json
    type: PostmanCollection
  description: Asynchronous request-logging endpoint for ingesting LLM call telemetry
    (model, prompt/completion messages, tokens, cost, latency, customer identifier,
    metadata) when calls are not routed through the gateway proxy.
- aid: keywordsai:prompts
  name: Keywords AI Prompts API
  tags:
  - Prompts
  - Prompt Management
  - Versioning
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.keywordsai.co/api-endpoints/prompt-endpoints/create-prompts
  baseURL: https://api.keywordsai.co/api
  properties:
  - url: https://docs.keywordsai.co/api-endpoints/prompt-endpoints/create-prompts
    type: Documentation
  - url: openapi/keywordsai-openapi.yml
    type: OpenAPI
  - url: collections/keywordsai.postman_collection.json
    type: PostmanCollection
  description: Manage prompts and prompt versions outside of application code -
    create, list, retrieve, update, and delete prompts; create, commit, and deploy
    versions with templated messages, models, fallbacks, and sampling parameters.
- aid: keywordsai:threads
  name: Keywords AI Threads API
  tags:
  - Threads
  - Conversations
  - Observability
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.keywordsai.co/api-endpoints/data-endpoints/list-threads
  baseURL: https://api.keywordsai.co/api
  properties:
  - url: https://docs.keywordsai.co/api-endpoints/data-endpoints/list-threads
    type: Documentation
  - url: openapi/keywordsai-openapi.yml
    type: OpenAPI
  - url: collections/keywordsai.postman_collection.json
    type: PostmanCollection
  description: Query multi-turn conversation threads grouped from logged LLM calls,
    with filtering and pagination for reconstructing end-user sessions.
- aid: keywordsai:evaluations
  name: Keywords AI Evaluations API
  tags:
  - Evaluations
  - Evaluators
  - Quality
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.keywordsai.co/api-endpoints/evaluator-endpoints/create-evaluator
  baseURL: https://api.keywordsai.co/api
  properties:
  - url: https://docs.keywordsai.co/api-endpoints/evaluator-endpoints/create-evaluator
    type: Documentation
  - url: openapi/keywordsai-openapi.yml
    type: OpenAPI
  - url: collections/keywordsai.postman_collection.json
    type: PostmanCollection
  description: Create and run evaluators to score LLM outputs - manage evaluator
    definitions and execute them against logs and datasets to measure quality,
    correctness, and safety.
- aid: keywordsai:traces
  name: Keywords AI Traces API
  tags:
  - Traces
  - OpenTelemetry
  - Observability
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.keywordsai.co/api-endpoints/data-endpoints/list-traces
  baseURL: https://api.keywordsai.co/api
  properties:
  - url: https://docs.keywordsai.co/api-endpoints/data-endpoints/list-traces
    type: Documentation
  - url: openapi/keywordsai-openapi.yml
    type: OpenAPI
  - url: collections/keywordsai.postman_collection.json
    type: PostmanCollection
  description: List, retrieve, and delete distributed traces (OpenTelemetry-aligned
    spans) capturing agent and multi-step LLM workflows for observability and
    debugging.
common:
- type: GitHubOrganization
  url: https://github.com/Keywords-AI
- type: LinkedIn
  url: https://www.linkedin.com/company/keywordsai
- type: Website
  url: https://www.keywordsai.co
- type: Documentation
  url: https://docs.keywordsai.co
- type: Plans
  url: plans/keywordsai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/keywordsai-rate-limits.yml
- type: FinOps
  url: finops/keywordsai-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com