---
title: "Openai Proxy Route"
method: PATCH
path: "/openai/{endpoint}"
tags: ["OpenAI Pass-through", "pass-through"]
---

# Openai Proxy Route

`PATCH /openai/{endpoint}`

Pass-through endpoint for OpenAI API calls.

Available on both routes:
- /openai/{endpoint:path} - Standard OpenAI passthrough route
- /openai_passthrough/{endpoint:path} - Dedicated passthrough route (recommended for Responses API)

Use /openai_passthrough/* when you need guaranteed passthrough to OpenAI without conflicts
with LiteLLM's native implementations (e.g., for the Responses API at /v1/responses).

Examples:
    Standard route:
    - /openai/v1/chat/completions
    - /openai/v1/assistants
    - /openai/v1/threads

    Dedicated passthrough (for Responses API):
    - /openai_passthrough/v1/responses
    - /openai_passthrough/v1/responses/{response_id}
    - /openai_passthrough/v1/responses/{response_id}/input_items

[Docs](https://docs.litellm.ai/docs/pass_through/openai_passthrough)

## Path parameters

- `endpoint` string, required

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/sea-lion/apis/litellm-api.md) · [All operations](https://skmtc.net/sea-lion/apis/litellm-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/sea-lion/litellm-api/revisions/79928a3d37d3/schema)