Cumulus Labs

aid: cumulus-labs
name: Cumulus Labs
description: Cumulus Labs is a Y Combinator (W26) company building a unified inference platform for production AI. Cumulus
  consolidates the eight subsystems teams normally assemble from separate vendors — an OpenAI-compatible gateway, a per-workflow
  router, a layered prompt/KV cache, request-level observability, continuous shadow evaluation, one-click LoRA fine-tuning,
  custom open-weight hosting, and the proprietary Ion inference engine running on NVIDIA Grace and Blackwell GPUs — behind
  a single OpenAI-compatible API at api.cumuluslabs.io/v1. Ion's custom attention kernels deliver 30-50% more throughput than
  stock vLLM and SGLang, and the gateway is a drop-in replacement for the OpenAI, Anthropic, LangChain, LlamaIndex, and Vercel
  AI SDKs — change one line of configuration and keep your existing code.
url: https://raw.githubusercontent.com/api-evangelist/cumulus-labs/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- y-combinator
- nvidia-inception
x-tier: profiled
x-tier-reason: enrichment-pass
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: '0.20'
created: '2026-07-17'
modified: '2026-07-18'
tags:
- Company
- Inference
- LLM
- AI Infrastructure
- GPU
- Machine Learning
- Model Serving
- Fine-Tuning
- API Gateway
- Y Combinator
image: https://cumuluslabs.io/cumulus-logo/Cumulus-White.svg
apis:
- name: Cumulus Inference Gateway
  description: OpenAI-compatible HTTP inference gateway. One client works against every upstream provider; per-workflow routing
    rules pick the model, provider, and infrastructure, with a layered exact/prefix/semantic cache, request-level observability,
    and the Ion engine serving open-weight models and fine-tunes.
  humanURL: https://docs.cumuluslabs.io/
  baseURL: https://api.cumuluslabs.io/v1
  tags:
  - Inference
  - LLM
  - OpenAI-Compatible
  - Gateway
  - GPU
  properties:
  - type: Documentation
    url: https://docs.cumuluslabs.io/
  - type: GettingStarted
    url: https://docs.cumuluslabs.io/getting-started/
  - type: APIReference
    url: https://docs.cumuluslabs.io/inference/overview/
  - type: Authentication
    url: authentication/cumulus-labs-authentication.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DomainSecurity
  url: security/cumulus-labs-domain-security.yml
- type: Website
  url: https://cumuluslabs.io/
- type: DeveloperPortal
  url: https://docs.cumuluslabs.io/
- type: Documentation
  url: https://docs.cumuluslabs.io/
- type: GettingStarted
  url: https://docs.cumuluslabs.io/getting-started/
- type: APIReference
  url: https://docs.cumuluslabs.io/inference/overview/
- type: Blog
  url: https://cumulus.blog/
- type: GitHubOrganization
  url: https://github.com/cumulus-compute-labs
- type: Support
  url: mailto:founders@cumuluslabs.io
- type: TermsOfService
  url: https://cumuluslabs.io/terms-of-service.pdf
- type: PrivacyPolicy
  url: https://cumuluslabs.io/privacy-policy.pdf
- type: LinkedIn
  url: https://www.linkedin.com/company/cumuluscomputelabs/
- type: Twitter
  url: https://x.com/cumuluslabsio
- type: Authentication
  url: authentication/cumulus-labs-authentication.yml
- type: Conventions
  url: conventions/cumulus-labs-conventions.yml
- type: Conformance
  url: conformance/cumulus-labs-conformance.yml
- type: Lifecycle
  url: lifecycle/cumulus-labs-lifecycle.yml
- type: LLMsTxt
  url: llms/cumulus-labs-llms.txt
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence