Reka

Reka is a multimodal foundation model company building natively multimodal large language models capable of joint reasoning over text, image, video, and audio. The Reka model family spans Spark (1B) for embedded use cases, Edge (7B), Flash (21B), and Core (67B) for complex enterprise tasks. Reka exposes its hosted models through the Reka API at api.reka.ai with OpenAI-compatible chat completions, and also ships products including the Reka Vision Platform for enterprise perception, Reka Speech for audio understanding, and Reka Clip for creators. The platform supports flexible deployment across cloud, VPC, on-premises, and fully air-gapped environments, and the company maintains an active open-source presence on Hugging Face and GitHub including the Reka VibeEval benchmark.

1 APIs 0 Features

AIMultimodalLarge Language ModelsVisionSpeechFoundation ModelsOpenAI CompatibleSDKEnterpriseOn-Premises

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Reka API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/chat
      body:
        type: json
        data: '{}'
    docs: 'Generate a chat completion from one of the Reka models. Supports

      multimodal inputs including text, images, video, and audio.

      '
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List available models
      type: http
    http:
      method: GET
      url: https://api.reka.ai/v1/models
    docs: Return the list of Reka models available to the caller.
- info:
    name: Videos
    type: folder
  items:
  - info:
      name: Upload a video
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/videos/upload
      body:
        type: multipart-form
        data:
        - name: file
          type: text
          value: ''
        - name: metadata
          type: text
          value: ''
    docs: Upload a video file to the Reka Vision platform.
  - info:
      name: List videos
      type: http
    http:
      method: GET
      url: https://api.reka.ai/v1/videos
      params:
      - name: limit
        value: ''
        type: query
        description: Maximum number of videos to return.
      - name: cursor
        value: ''
        type: query
        description: Pagination cursor.
    docs: List videos uploaded to the caller's account.
  - info:
      name: Get a video
      type: http
    http:
      method: GET
      url: https://api.reka.ai/v1/videos/:video_id
      params:
      - name: video_id
        value: ''
        type: path
    docs: Retrieve metadata for a specific uploaded video.
  - info:
      name: Delete a video
      type: http
    http:
      method: DELETE
      url: https://api.reka.ai/v1/videos/:video_id
      params:
      - name: video_id
        value: ''
        type: path
    docs: Delete a video and its associated indexes.
- info:
    name: VideoGroups
    type: folder
  items:
  - info:
      name: List video groups
      type: http
    http:
      method: GET
      url: https://api.reka.ai/v1/video-groups
    docs: List video groups owned by the caller.
  - info:
      name: Create a video group
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/video-groups
      body:
        type: json
        data: '{}'
    docs: Create a new named group of videos.
- info:
    name: Search
    type: folder
  items:
  - info:
      name: Search videos
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/search
      body:
        type: json
        data: '{}'
    docs: Search across uploaded videos with a natural-language query.
- info:
    name: QA
    type: folder
  items:
  - info:
      name: Video Q&A chat
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/qa/chat
      body:
        type: json
        data: '{}'
    docs: 'Ask conversational questions over an uploaded video or video group

      with multi-turn context.

      '
- info:
    name: Clips
    type: folder
  items:
  - info:
      name: Create clips
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/clips
      body:
        type: json
        data: '{}'
    docs: Generate clips from a video by prompt or query.
- info:
    name: Speech
    type: folder
  items:
  - info:
      name: Transcribe or translate audio
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/speech/transcribe-translate
      body:
        type: multipart-form
        data:
        - name: file
          type: text
          value: ''
        - name: mode
          type: text
          value: ''
        - name: target_language
          type: text
          value: ''
    docs: Transcribe or translate spoken audio with multimodal reasoning.
- info:
    name: Research
    type: folder
  items:
  - info:
      name: Research chat with web search
      type: http
    http:
      method: POST
      url: https://api.reka.ai/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: 'OpenAI-compatible chat completions endpoint, including Reka Research

      models that can browse the web and return citations.

      '
bundled: true

Reka

APIs

Reka API

Collections

Reka API

Pricing Plans

Reka Plans Pricing

Rate Limits

Reka Rate Limits

FinOps

Reka Finops

Resources

Sources