---
title: "Create cached content (Gemini format)"
method: POST
path: "/genai/v1beta/cachedContents"
tags: ["GenAI Integration"]
---

# Create cached content (Gemini format)

`POST /genai/v1beta/cachedContents`

Creates a cached content entry that can be re-used across subsequent
generate-content calls to reduce repeated prefix tokens.

## Headers

- `x-model-provider` string

## Request body

- object
  - `model` string, required — Gemini model identifier (e.g. `gemini-1.5-pro`). The `models/` prefix is stripped.
  - `displayName` string
  - `systemInstruction` object — System instruction content.
  - `contents` unknown[]
    - unknown
  - `tools` unknown[]
    - unknown
  - `toolConfig` unknown
  - `ttl` string — TTL in protobuf duration format (e.g. `3600s`).
  - `expireTime` string, date-time

## Response `200`

Successful response

- object

## Other responses

- `400` — Bad request
- `500` — Internal server error

---

[API](https://skmtc.net/getbifrost/apis/bifrost-api.md) · [All operations](https://skmtc.net/getbifrost/apis/bifrost-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/getbifrost/bifrost-api/versions/f8cab88f64ea/schema)