Bring any OpenAI-compatible endpointEnterprise

Custom Providers

Plug private, self-hosted or niche OpenAI-compatible endpoints into the gateway and call them like any other model.

Get startedRead the docs
Your app → LLM Gateway
Your appLLM Gatewaymycompany/vllmself-hostedinternal/tunedprivateopenai/gpt-5catalog
Custom and catalog models, one API
01

Any compatible API

If it speaks OpenAI, it plugs in.

02

Custom catalog

Define your own models in the directory.

03

Same tooling

Keys, logs and analytics included.

04

Compliance aware

Attest providers for your policy.

Built for

  • Private deployments

    vLLM, TGI or in-house models

  • Fine-tunes

    Serve them next to frontier models

  • Regional hosts

    Keep data in your own region

Call your provider
terminal
1curl https://api.llmgateway.io/v1/chat/completions \2  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "model": "mycompany/custom-gpt-4",6    "messages": [7      {8        "role": "user",9        "content": "Hello!"10      }11    ]12  }'
Read docs

More in routing & reliability

All features

Caching

Pay once for repeated work

Request Timeouts

Per-attempt limits that suit agents

Unified API Interface

One API for all LLM providers

Start using Custom Providers today

One API key. Every model. Live in minutes.

Start buildingBrowse models