Literal AI logo

Literal AI

Literal AI is the collaborative observability, evaluation, and analytics platform for building production-grade LLM applications, from the Chainlit team. Its API is GraphQL (POST /api/graphql) consumed through Python and TypeScript SDKs, capturing threads, steps, generations, datasets, experiments, prompts, and scores, with an additional OpenTelemetry (OTLP) ingestion path for traces.

6 APIs 0 Features
AILLMObservabilityEvaluationMonitoring

APIs

Literal AI Threads & Steps API

Create, read, update, upsert, and delete conversation threads and the nested steps (runs, tools, retrievals, LLM calls) that trace an LLM application's execution, queried and mu...

Literal AI Generations API

Log and paginate chat and completion generations - prompts, model, settings, token usage, and outputs - with filtering for analytics and evaluation.

Literal AI Datasets API

Build and manage datasets and dataset items - curated from production steps or created manually - that serve as ground truth for evaluation and experiments.

Literal AI Experiments API

Create dataset experiments and record per-item experiment runs with scores to benchmark prompt, model, and pipeline changes over time.

Literal AI Prompts API

Version, store, and retrieve prompt templates with their model settings, enabling collaborative prompt engineering and A/B testing against deployed apps.

Literal AI Scores API

Attach human, AI, and code-based scores to steps and generations - numeric, categorical, or boolean - for feedback collection and offline/online evaluation.

Resources

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

Sources

Raw ↑
aid: literalai
url: https://raw.githubusercontent.com/api-evangelist/literalai/refs/heads/main/apis.yml
name: Literal AI
kind: company
description: Literal AI is the collaborative observability, evaluation, and analytics
  platform for building production-grade LLM applications, from the Chainlit team.
  Its API is GraphQL (POST /api/graphql) consumed through Python and TypeScript SDKs,
  capturing threads, steps, generations, datasets, experiments, prompts, and scores,
  with an additional OpenTelemetry (OTLP) ingestion path for traces.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
- AI
- LLM
- Observability
- Evaluation
- Monitoring
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: literalai:threads-steps
  name: Literal AI Threads & Steps API
  tags:
  - Threads
  - Steps
  - Tracing
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.literalai.com/python-client/api-reference/api
  baseURL: https://cloud.getliteral.ai/api/graphql
  properties:
  - url: https://docs.literalai.com/observability/concepts
    type: Documentation
  - url: https://docs.literalai.com/python-client/api-reference/api
    type: APIReference
  - url: openapi/literalai-openapi.yml
    type: OpenAPI
  - url: graphql/literalai-graphql.md
    type: GraphQL
  description: Create, read, update, upsert, and delete conversation threads and the
    nested steps (runs, tools, retrievals, LLM calls) that trace an LLM application's
    execution, queried and mutated over GraphQL.
- aid: literalai:generations
  name: Literal AI Generations API
  tags:
  - Generations
  - LLM
  - Logging
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.literalai.com/python-client/api-reference/api
  baseURL: https://cloud.getliteral.ai/api/graphql
  properties:
  - url: https://docs.literalai.com/observability/concepts
    type: Documentation
  - url: https://docs.literalai.com/python-client/api-reference/api
    type: APIReference
  - url: openapi/literalai-openapi.yml
    type: OpenAPI
  - url: graphql/literalai-graphql.md
    type: GraphQL
  description: Log and paginate chat and completion generations - prompts, model,
    settings, token usage, and outputs - with filtering for analytics and evaluation.
- aid: literalai:datasets
  name: Literal AI Datasets API
  tags:
  - Datasets
  - Evaluation
  - Test Data
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.literalai.com/python-client/api-reference/api
  baseURL: https://cloud.getliteral.ai/api/graphql
  properties:
  - url: https://docs.literalai.com/evaluation/datasets
    type: Documentation
  - url: https://docs.literalai.com/python-client/api-reference/api
    type: APIReference
  - url: openapi/literalai-openapi.yml
    type: OpenAPI
  - url: graphql/literalai-graphql.md
    type: GraphQL
  description: Build and manage datasets and dataset items - curated from production
    steps or created manually - that serve as ground truth for evaluation and experiments.
- aid: literalai:experiments
  name: Literal AI Experiments API
  tags:
  - Experiments
  - Evaluation
  - Benchmarking
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.literalai.com/python-client/api-reference/api
  baseURL: https://cloud.getliteral.ai/api/graphql
  properties:
  - url: https://docs.literalai.com/evaluation/experiments
    type: Documentation
  - url: https://docs.literalai.com/python-client/api-reference/api
    type: APIReference
  - url: openapi/literalai-openapi.yml
    type: OpenAPI
  - url: graphql/literalai-graphql.md
    type: GraphQL
  description: Create dataset experiments and record per-item experiment runs with
    scores to benchmark prompt, model, and pipeline changes over time.
- aid: literalai:prompts
  name: Literal AI Prompts API
  tags:
  - Prompts
  - Versioning
  - Templates
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.literalai.com/python-client/api-reference/api
  baseURL: https://cloud.getliteral.ai/api/graphql
  properties:
  - url: https://docs.literalai.com/prompt-engineering/prompts
    type: Documentation
  - url: https://docs.literalai.com/python-client/api-reference/api
    type: APIReference
  - url: openapi/literalai-openapi.yml
    type: OpenAPI
  - url: graphql/literalai-graphql.md
    type: GraphQL
  description: Version, store, and retrieve prompt templates with their model settings,
    enabling collaborative prompt engineering and A/B testing against deployed apps.
- aid: literalai:scores
  name: Literal AI Scores API
  tags:
  - Scores
  - Feedback
  - Evaluation
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.literalai.com/python-client/api-reference/api
  baseURL: https://cloud.getliteral.ai/api/graphql
  properties:
  - url: https://docs.literalai.com/evaluation/scores
    type: Documentation
  - url: https://docs.literalai.com/python-client/api-reference/api
    type: APIReference
  - url: openapi/literalai-openapi.yml
    type: OpenAPI
  - url: graphql/literalai-graphql.md
    type: GraphQL
  description: Attach human, AI, and code-based scores to steps and generations -
    numeric, categorical, or boolean - for feedback collection and offline/online
    evaluation.
common:
- type: GitHubOrganization
  url: https://github.com/Chainlit
- type: LinkedIn
  url: https://www.linkedin.com/company/chainlit
- type: Website
  url: https://www.literalai.com
- type: Documentation
  url: https://docs.literalai.com
- type: Plans
  url: plans/literalai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/literalai-rate-limits.yml
- type: FinOps
  url: finops/literalai-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com