.txt

aid: txt
name: .txt
description: '.txt (dottxt) is the structured-generation company behind the open-source Outlines library (65M+ downloads).
  Its hosted platform, the dottxt API at api.dottxt.ai, is an OpenAI-compatible pay-per-token API whose defining contract
  is schema enforcement: a JSON Schema passed in response_format is compiled and enforced by constrained decoding, so model
  outputs are guaranteed valid — including field-by-field RFC 6902 JSON Patch streaming, Open Responses support, embeddings,
  and JSONL batch processing. Founded by the Outlines maintainers and backed by Seedcamp; inference is operated with launch
  partner Doubleword.'
url: https://raw.githubusercontent.com/api-evangelist/txt/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- seedcamp
x-tier: stub
x-tier-reason: portfolio-lead
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.23'
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 21
  pass: local-v1
created: '2026-07-17'
modified: '2026-07-21'
image: https://cdn.sanity.io/images/z84vkf2c/production/f496d7868262fbf26f71782579181541f75b45b5-100x50.svg
tags:
- Company
- Artificial Intelligence
- LLM
- Structured Outputs
- JSON-Schema
- Inference
- Developer Tools
- Machine-Learning
tags_raw:
- Company
- Artificial Intelligence
- LLM
- Structured Outputs
- JSON Schema
- Inference
- Developer Tools
- Machine Learning
apis:
- aid: txt:txt-batches-api
  name: .txt batches API
  description: 'Process large volumes of requests asynchronously.


    Batch processing is ideal when you:

    - Have many requests that don''t need immediate responses

    - Want to process data in bulk (e.g., embeddings for a document corpus)

    - Are running offline evaluations or data pipelines


    Choose your completion window: 1 hour or 24 hours. You can track progress, cancel in-flight batches, and retry failed
    requests.


    [Getting started with the Batch API →](https://docs.doubleword.ai/batches/getting-started-with-batched-api)'
  humanURL: https://docs.dottxt.ai/api/overview
  baseURL: https://api.dottxt.ai/v1
  tags:
  - Batches
  tags_raw:
  - batches
  properties:
  - type: OpenAPI
    url: openapi/txt-batches-api-openapi.yml
  - type: Documentation
    url: https://docs.dottxt.ai/api/overview
  - type: APIReference
    url: https://docs.dottxt.ai/api/chat-completions
- aid: txt:txt-chat-api
  name: .txt chat API
  description: 'Create model responses for chat conversations.


    Supports:

    - **Multi-turn dialogue** with conversation history

    - **System prompts** to control model behavior

    - **Tool calling** for function execution and structured outputs

    - **Streaming** for real-time token delivery

    - **Sampling parameters** like temperature, top_p, and frequency penalties'
  humanURL: https://docs.dottxt.ai/api/overview
  baseURL: https://api.dottxt.ai/v1
  tags:
  - Chat
  tags_raw:
  - chat
  properties:
  - type: OpenAPI
    url: openapi/txt-chat-api-openapi.yml
  - type: Documentation
    url: https://docs.dottxt.ai/api/overview
  - type: APIReference
    url: https://docs.dottxt.ai/api/chat-completions
- aid: txt:txt-embeddings-api
  name: .txt embeddings API
  description: 'Generate vector representations of text.


    Use embeddings for:

    - **Semantic search** - find content by meaning, not just keywords

    - **Clustering** - group similar documents together

    - **Classification** - categorize text based on similarity to examples

    - **Recommendations** - suggest related content'
  humanURL: https://docs.dottxt.ai/api/overview
  baseURL: https://api.dottxt.ai/v1
  tags:
  - Embeddings
  tags_raw:
  - embeddings
  properties:
  - type: OpenAPI
    url: openapi/txt-embeddings-api-openapi.yml
  - type: Documentation
    url: https://docs.dottxt.ai/api/overview
  - type: APIReference
    url: https://docs.dottxt.ai/api/chat-completions
- aid: txt:txt-files-api
  name: .txt files API
  description: 'Upload and manage JSONL files for batch processing.


    Each line in the file should be a JSON object with:

    - `custom_id` - your identifier for tracking the request

    - `method` - HTTP method (POST)

    - `url` - endpoint path (e.g., `/v1/chat/completions`)

    - `body` - the request payload


    [Learn more about the JSONL file format →](https://docs.doubleword.ai/batches/jsonl-files)'
  humanURL: https://docs.dottxt.ai/api/overview
  baseURL: https://api.dottxt.ai/v1
  tags:
  - File
  tags_raw:
  - files
  properties:
  - type: OpenAPI
    url: openapi/txt-files-api-openapi.yml
  - type: Documentation
    url: https://docs.dottxt.ai/api/overview
  - type: APIReference
    url: https://docs.dottxt.ai/api/chat-completions
- aid: txt:txt-models-api
  name: .txt models API
  description: 'List and retrieve information about available models.


    Use these endpoints to discover which models you have access to and their capabilities.'
  humanURL: https://docs.dottxt.ai/api/overview
  baseURL: https://api.dottxt.ai/v1
  tags:
  - Models
  tags_raw:
  - models
  properties:
  - type: OpenAPI
    url: openapi/txt-models-api-openapi.yml
  - type: Documentation
    url: https://docs.dottxt.ai/api/overview
  - type: APIReference
    url: https://docs.dottxt.ai/api/chat-completions
- aid: txt:txt-responses-api-api
  name: .txt responses-api API
  description: 'Create model responses with enhanced capabilities.


    Open Responses compatible endpoint providing advanced features:


    - **Reasoning models** - Control computational effort with `reasoning` parameter

    - **Stateful conversations** - Maintain context across turns with `previous_response_id`

    - **Flexible input** - Use simple strings or full message arrays

    - **Text output configuration** - Structured outputs via `text` parameter

    - **Context management** - Handle overflow with `truncation` parameter


    [Open Responses API Reference →](https://www.openresponses.org/reference)'
  humanURL: https://docs.dottxt.ai/api/overview
  baseURL: https://api.dottxt.ai/v1
  tags:
  - Responses API
  tags_raw:
  - responses-api
  properties:
  - type: OpenAPI
    url: openapi/txt-responses-api-api-openapi.yml
  - type: Documentation
    url: https://docs.dottxt.ai/api/overview
  - type: APIReference
    url: https://docs.dottxt.ai/api/chat-completions
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Overlay
  url: overlays/txt-dottxt-overlay.yaml
- type: Website
  url: https://dottxt.ai
- type: Documentation
  url: https://docs.dottxt.ai
- type: APIReference
  url: https://docs.dottxt.ai/api/overview
- type: GettingStarted
  url: https://docs.dottxt.ai/quickstart
- type: SignUp
  url: https://h1xbpbfsf0w.typeform.com/to/fwQNWmS8
- type: Blog
  url: https://blog.dottxt.ai/
- type: GitHubOrganization
  url: https://github.com/dottxt-ai
- type: Support
  url: https://discord.gg/ErZ8XnCmkQ
- type: PrivacyPolicy
  url: https://dottxt.ai/privacy-policy
- type: LLMsTxt
  url: llms/txt-llms.txt
- type: Packages
  url: packages/txt-packages.yml
- type: SDKs
  url: packages/txt-packages.yml
- type: CLI
  url: cli/txt-cli.yml
- type: WellKnown
  url: well-known/txt-well-known.yml
- type: MCPServer
  url: mcp/txt-mcp.yml
- type: Conformance
  url: conformance/txt-conformance.yml
- type: ErrorCatalog
  url: errors/txt-problem-types.yml
- type: Lifecycle
  url: lifecycle/txt-lifecycle.yml
- type: ChangeLog
  url: changelog/txt-changelog.yml
- type: Authentication
  url: authentication/txt-authentication.yml
- type: Conventions
  url: conventions/txt-conventions.yml
- type: DataModel
  url: data-model/txt-data-model.yml
- type: AgentSkill
  url: skills/_index.yml
- type: AgenticAccess
  url: agentic-access/txt-agentic-access.yml
- type: DomainSecurity
  url: security/txt-domain-security.yml