FlexAI

FlexAI is managed inference for builders — an OpenAI-compatible API (Token Factory) that provides a single API key across open models for text, code, reasoning, vision, embeddings, image, video, and audio, priced by usage per model. Beyond serverless inference the platform offers dedicated GPU endpoints, managed LoRA/QLoRA fine-tuning, distributed training, an Agent SDK (in trial), and a private AI cloud (AI Factory) deployable to VPC, on-prem, or air-gapped environments. Because the inference API is a drop-in OpenAI replacement, teams point the OpenAI SDK at the FlexAI base URL and change only the key. FlexAI is backed by Partech and profiled in the API Evangelist network for its developer surface and agent-native infrastructure.

FlexAI publishes 7 APIs on the APIs.io network, including Audio API, Chat API, Completions API, and 4 more. Tagged areas include Company, Ai/Ml, Artificial Intelligence, Machine Learning, and Inference.

FlexAI’s developer surface includes documentation, API reference, getting-started guide, engineering blog, pricing, signup flow, support, and 21 more developer resources.

🌐 Visit website 📡 Source on GitHub
61.3/100 strong ▬ flat Agent 72/100 agent native Full breakdown ↓
scored 2026-07-23 · rubric v0.5
AccessEnterpriseSelf serve
7 APIs 1 MCP Servers
CompanyAi/MlArtificial IntelligenceMachine LearningInferenceLLMLarge Language ModelsOpenAI CompatibleGPU ComputeEmbeddingsFine-TuningAgents

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-23 · rubric v0.5
Composite quality — 61.3/100 · strong
Contract Quality 14.9 / 25
Developer Ergonomics 13.5 / 20
Commercial Clarity 16.8 / 20
Operational Transparency 6.2 / 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/flexai: 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 7

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

FlexAI Audio API

Speech-to-text and text-to-speech

FlexAI Chat API

Chat completions

FlexAI Completions API

Legacy text completions

FlexAI Embeddings API

Vector embeddings

FlexAI Images API

Image generation

FlexAI Models API

Model catalog

FlexAI Video API

Video generation

Scroll for all 7

MCP Servers 1

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

flexai-mcp.yml

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Flexai Plans

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Flexai Rate Limits

3 limits

RATE LIMITS

Security Posture 2

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

Flexai Authentication

http · 1 scheme

SECURITY

Flexai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

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

Flexai Agentic Access

8 operations · 7 acting

8 operations · 7 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

DeveloperPortal
DeveloperPortal
 GettingStarted
GettingStarted
 SignUp
SignUp

Documentation 3

Reference material describing how the API behaves

Documentation
Documentation
 APIReference
APIReference
 OpenAPI
OpenAPI

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess
AgenticAccess
 LLMsTxt
LLMsTxt
 MCPServer
MCPServer
 AgentSkill
AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions
Conventions
 ErrorCatalog
ErrorCatalog
 Lifecycle
Lifecycle
 Conformance
Conformance
 DataModel
DataModel

Access & Security 3

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity
 TrustCenter
TrustCenter
 Authentication
Authentication

Operate 3

Status, limits, changes, and where to get help

Support
Support
 StatusPage
StatusPage
 RateLimits
RateLimits

Commercial 4

Pricing, plans, and the legal terms of use

Pricing
Pricing
 TermsOfService
TermsOfService
 PrivacyPolicy
PrivacyPolicy
 Plans
Plans

Company 2

The organization behind the API

Website
Website
 Blog
Blog

Other 1

Properties that don't map to a standard resource type

Overlay
Overlay

Source (apis.yml)

apis.yml Raw ↑ 
aid: flexai
accessModel:
  pricing: enterprise
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Enterprise · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/flexai.png
name: FlexAI
description: FlexAI is managed inference for builders — an OpenAI-compatible API (Token Factory) that provides a single API
  key across open models for text, code, reasoning, vision, embeddings, image, video, and audio, priced by usage per model.
  Beyond serverless inference the platform offers dedicated GPU endpoints, managed LoRA/QLoRA fine-tuning, distributed training,
  an Agent SDK (in trial), and a private AI cloud (AI Factory) deployable to VPC, on-prem, or air-gapped environments. Because
  the inference API is a drop-in OpenAI replacement, teams point the OpenAI SDK at the FlexAI base URL and change only the
  key. FlexAI is backed by Partech and profiled in the API Evangelist network for its developer surface and agent-native infrastructure.
url: https://raw.githubusercontent.com/api-evangelist/flexai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- partech
x-tier: stub
x-tier-reason: portfolio-lead
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-19'
tags:
- Company
- Ai/Ml
- Artificial Intelligence
- Machine Learning
- Inference
- LLM
- Large Language Models
- OpenAI Compatible
- GPU Compute
- Embeddings
- Fine-Tuning
- Agents
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
apis:
- aid: flexai:flexai-audio-api
  name: FlexAI Audio API
  description: Speech-to-text and text-to-speech
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Audio
  properties:
  - type: OpenAPI
    url: openapi/flexai-audio-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
- aid: flexai:flexai-chat-api
  name: FlexAI Chat API
  description: Chat completions
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/flexai-chat-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
- aid: flexai:flexai-completions-api
  name: FlexAI Completions API
  description: Legacy text completions
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Completions
  properties:
  - type: OpenAPI
    url: openapi/flexai-completions-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
- aid: flexai:flexai-embeddings-api
  name: FlexAI Embeddings API
  description: Vector embeddings
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Embeddings
  properties:
  - type: OpenAPI
    url: openapi/flexai-embeddings-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
- aid: flexai:flexai-images-api
  name: FlexAI Images API
  description: Image generation
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Images
  properties:
  - type: OpenAPI
    url: openapi/flexai-images-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
- aid: flexai:flexai-models-api
  name: FlexAI Models API
  description: Model catalog
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/flexai-models-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
- aid: flexai:flexai-video-api
  name: FlexAI Video API
  description: Video generation
  humanURL: https://docs.flex.ai/inference-api/overview
  baseURL: https://tokens.flex.ai/v1
  tags:
  - Video
  properties:
  - type: OpenAPI
    url: openapi/flexai-video-api-openapi.yml
  - type: Documentation
    url: https://docs.flex.ai
  - type: APIReference
    url: https://docs.flex.ai/inference-api/reference/openai-compatibility
  - type: GettingStarted
    url: https://docs.flex.ai/inference-api/quickstart
  - type: Authentication
    url: authentication/flexai-authentication.yml
common:
- type: DomainSecurity
  url: security/flexai-domain-security.yml
- type: AgenticAccess
  url: agentic-access/flexai-agentic-access.yml
- type: Website
  url: https://www.flex.ai/
- type: DeveloperPortal
  url: https://docs.flex.ai
- type: Documentation
  url: https://docs.flex.ai
- type: APIReference
  url: https://docs.flex.ai/inference-api/reference/openai-compatibility
- type: GettingStarted
  url: https://docs.flex.ai/inference-api/quickstart
- type: Blog
  url: https://flex.ai/blog
- type: Pricing
  url: https://flex.ai/pricing
- type: SignUp
  url: https://tokens.flex.ai/signup
- type: Support
  url: mailto:support@flex.ai
- type: TermsOfService
  url: https://flex.ai/terms-of-service
- type: PrivacyPolicy
  url: https://flex.ai/privacy-policy
- type: StatusPage
  url: https://status.flex.ai
- type: TrustCenter
  url: https://security.flex.ai
- type: LLMsTxt
  url: llms/flexai-llms.txt
- type: OpenAPI
  url: openapi/flexai-token-factory-openapi.yml
- type: Authentication
  url: authentication/flexai-authentication.yml
- type: Conventions
  url: conventions/flexai-conventions.yml
- type: RateLimits
  url: rate-limits/flexai-rate-limits.yml
- type: ErrorCatalog
  url: errors/flexai-problem-types.yml
- type: Lifecycle
  url: lifecycle/flexai-lifecycle.yml
- type: Conformance
  url: conformance/flexai-conformance.yml
- type: DataModel
  url: data-model/flexai-data-model.yml
- type: MCPServer
  url: mcp/flexai-mcp.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Overlay
  url: overlays/flexai-token-factory-overlay.yaml
- type: Plans
  url: plans/flexai-plans.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence