Pruna AI

Pruna AI builds Performance Models (P-Series) — optimized image and video generation models engineered to be faster, cheaper, and smaller than standard alternatives while keeping quality high. It ships three ways: a hosted HTTP API (P-API) that exposes ~20 models (text-to-image, image editing, upscaling, virtual try-on, text/image-to-video, avatar, animation and replacement, plus LoRA trainers) behind a single endpoint selected via a request header; an open-source Python optimization framework (pruna / pruna-pro) for caching, quantization, pruning, distillation and compilation of your own models; and hosted demos. The P-API uses apikey-header auth with an async submit/poll/download workflow and an optional synchronous mode. Pruna AI is a portfolio company of EQT Ventures.

Pruna AI publishes 3 APIs on the APIs.io network: Content Delivery API, File Management API, and Predictions API. Tagged areas include Company, Artificial Intelligence, Machine Learning, Image Generation, and Video Generation.

Pruna AI’s developer surface includes documentation, API reference, getting-started guide, signup flow, pricing, engineering blog, support, and 20 more developer resources.

🌐 Visit website 📡 Source on GitHub
51.2/100 developing ▬ flat Agent 72/100 agent native Full breakdown ↓
scored 2026-07-28 · rubric v0.5
AccessSelf serve
3 APIs 1 MCP Servers
CompanyArtificial IntelligenceMachine LearningImage GenerationVideo GenerationGenerative AIModel OptimizationInferenceDeveloper Tools

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-28 · rubric v0.5
Composite quality — 51.2/100 · developing
Contract Quality 15.5 / 25
Developer Ergonomics 16.1 / 20
Commercial Clarity 8.9 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 72/100 · agent native
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/pruna-ai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 3

Individual APIs this provider publishes, each with its own machine-readable definition.

Pruna AI Content Delivery API

Download generated content files

Pruna AI File Management API

Upload files to be used as input for predictions

Pruna AI Predictions API

Core prediction workflow operations

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

pruna-ai-mcp.yml

MCP SERVER

Rate Limits 1

Documented rate limits and quota policies.

Pruna Ai Rate Limits

0 limits

RATE LIMITS

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Pruna Ai Authentication

apiKey · 1 scheme

SECURITY

Pruna Ai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Pruna Ai Agentic Access

4 operations · 2 acting

4 operations · 2 acting

AGENTIC

Resources

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp
 Sandbox
Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

MCPServer
MCPServer
 LLMsTxt
LLMsTxt
 AgentSkill
AgentSkill
 AgenticAccess
AgenticAccess

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 Conformance
Conformance
 DataModel
DataModel

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization
 Packages
Packages
 SDKs
SDKs

Access & Security 2

Authentication, authorization, and security posture

Authentication
Authentication
 DomainSecurity
DomainSecurity

Operate 2

Status, limits, changes, and where to get help

Support
Support
 RateLimits
RateLimits

Commercial 3

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy

Company 2

The organization behind the API

Blog
Blog
 Website
Website

Source (apis.yml)

apis.yml Raw ↑ 
aid: pruna-ai
name: Pruna AI
description: 'Pruna AI builds Performance Models (P-Series) — optimized image and video generation models engineered to be
  faster, cheaper, and smaller than standard alternatives while keeping quality high. It ships three ways: a hosted HTTP API
  (P-API) that exposes ~20 models (text-to-image, image editing, upscaling, virtual try-on, text/image-to-video, avatar, animation
  and replacement, plus LoRA trainers) behind a single endpoint selected via a request header; an open-source Python optimization
  framework (pruna / pruna-pro) for caching, quantization, pruning, distillation and compilation of your own models; and hosted
  demos. The P-API uses apikey-header auth with an async submit/poll/download workflow and an optional synchronous mode. Pruna
  AI is a portfolio company of EQT Ventures.'
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
image: https://framerusercontent.com/images/tM3dYw39zvWf45dsZXfTkZm0jNc.png
url: https://raw.githubusercontent.com/api-evangelist/pruna-ai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- eqt-ventures
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 19
  pass: local-v1
tags:
- Company
- Artificial Intelligence
- Machine Learning
- Image Generation
- Video Generation
- Generative AI
- Model Optimization
- Inference
- Developer Tools
apis:
- aid: pruna-ai:pruna-ai-content-delivery-api
  name: Pruna AI Content Delivery API
  description: Download generated content files
  humanURL: https://docs.api.pruna.ai/
  baseURL: https://api.pruna.ai
  tags:
  - Content Delivery
  properties:
  - type: OpenAPI
    url: openapi/pruna-ai-content-delivery-api-openapi.yml
  - type: Documentation
    url: https://docs.api.pruna.ai/
  - type: APIReference
    url: https://docs.api.pruna.ai/apis/models-api-0/versions/d086a242-3813-4148-a087-e724d4b333f8
  - type: GettingStarted
    url: https://docs.api.pruna.ai/guides/quickstart
- aid: pruna-ai:pruna-ai-file-management-api
  name: Pruna AI File Management API
  description: Upload files to be used as input for predictions
  humanURL: https://docs.api.pruna.ai/
  baseURL: https://api.pruna.ai
  tags:
  - File Management
  properties:
  - type: OpenAPI
    url: openapi/pruna-ai-file-management-api-openapi.yml
  - type: Documentation
    url: https://docs.api.pruna.ai/
  - type: APIReference
    url: https://docs.api.pruna.ai/apis/models-api-0/versions/d086a242-3813-4148-a087-e724d4b333f8
  - type: GettingStarted
    url: https://docs.api.pruna.ai/guides/quickstart
- aid: pruna-ai:pruna-ai-predictions-api
  name: Pruna AI Predictions API
  description: Core prediction workflow operations
  humanURL: https://docs.api.pruna.ai/
  baseURL: https://api.pruna.ai
  tags:
  - Predictions
  properties:
  - type: OpenAPI
    url: openapi/pruna-ai-predictions-api-openapi.yml
  - type: Documentation
    url: https://docs.api.pruna.ai/
  - type: APIReference
    url: https://docs.api.pruna.ai/apis/models-api-0/versions/d086a242-3813-4148-a087-e724d4b333f8
  - type: GettingStarted
    url: https://docs.api.pruna.ai/guides/quickstart
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DeveloperPortal
  url: https://docs.api.pruna.ai/
- type: Documentation
  url: https://docs.pruna.ai/en/stable/
- type: APIReference
  url: https://docs.api.pruna.ai/apis/models-api-0/versions/d086a242-3813-4148-a087-e724d4b333f8
- type: GettingStarted
  url: https://docs.api.pruna.ai/guides/quickstart
- type: SignUp
  url: https://dashboard.pruna.ai/login
- type: Pricing
  url: https://www.pruna.ai/pricing
- type: Blog
  url: https://www.pruna.ai/blog
- type: Support
  url: https://discord.gg/JFQmtFKCjd
- type: GitHubOrganization
  url: https://github.com/PrunaAI
- type: TermsOfService
  url: https://docs.api.pruna.ai/terms
- type: PrivacyPolicy
  url: https://www.pruna.ai/privacy-notice
- type: Sandbox
  url: https://demo.pruna.ai/
- type: Authentication
  url: authentication/pruna-ai-authentication.yml
- type: Conventions
  url: conventions/pruna-ai-conventions.yml
- type: ErrorCatalog
  url: errors/pruna-ai-problem-types.yml
- type: Lifecycle
  url: lifecycle/pruna-ai-lifecycle.yml
- type: Conformance
  url: conformance/pruna-ai-conformance.yml
- type: DataModel
  url: data-model/pruna-ai-data-model.yml
- type: RateLimits
  url: rate-limits/pruna-ai-rate-limits.yml
- type: Packages
  url: packages/pruna-ai-packages.yml
- type: SDKs
  url: packages/pruna-ai-packages.yml
- type: MCPServer
  url: mcp/pruna-ai-mcp.yml
- type: LLMsTxt
  url: llms/pruna-ai-llms.txt
- type: AgentSkill
  url: skills/_index.yml
- type: AgenticAccess
  url: agentic-access/pruna-ai-agentic-access.yml
- type: DomainSecurity
  url: security/pruna-ai-domain-security.yml
- type: Website
  url: https://www.pruna.ai/