---
title: "Create Fallback"
method: POST
path: "/fallback"
tags: ["Fallback Management"]
---

# Create Fallback

`POST /fallback`

Create or update fallbacks for a specific model.

This endpoint allows you to configure fallback models separately from the general config.
Fallbacks are triggered when a model call fails after retries.

**Example Request:**
```json
{
    "model": "gpt-3.5-turbo",
    "fallback_models": ["gpt-4", "claude-3-haiku"],
    "fallback_type": "general"
}
```

**Fallback Types:**
- `general`: Standard fallbacks for any error (default)
- `context_window`: Fallbacks specifically for context window exceeded errors
- `content_policy`: Fallbacks specifically for content policy violations

## Request body

- FallbackCreateRequest — Request model for creating/updating fallbacks
  - `model` string, required — The model name to configure fallbacks for (e.g., 'gpt-3.5-turbo')
  - `fallback_models` string[], required — List of fallback model names in order of priority
  - `fallback_type` 'general' | 'context_window' | 'content_policy' — Type of fallback: 'general' (default), 'context_window', or 'content_policy'

## Response `200`

Successful Response

- FallbackResponse — Response model for fallback operations
  - `model` string, required — The model name
  - `fallback_models` string[], required — List of fallback model names
  - `fallback_type` string, required — Type of fallback
  - `message` string, required — Success message

## 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/1e929292ddd5/schema)