# gemini-video-vision

> Gemini Video Vision uses Google Gemini's native video understanding to analyze and describe video content in detail — motion, composition, subjects, on-screen text, and more. Upload a video URL and a prompt, and Gemini returns a detailed text analysis. Token-based pricing.

## Overview

- **Endpoint**: `POST https://api.muapi.ai/api/v1/gemini-video-vision`
- **Model ID**: `gemini-video-vision`
- **Category**: text to text
- **Variant**: Gemini Video Vision
- **Family**: video-understanding
- **Cost**: 0.004 credits per call (some models compute cost dynamically based on params)

## API Usage

MuApi uses a **submit-then-poll** pattern: submit a job, get a `request_id`, then poll the predictions endpoint until `status` is `completed`. Optionally pass `?webhook=YOUR_URL` on the submit call to receive a POST callback when the job finishes (skip polling).

**Authentication**: send your MuApi key in the `x-api-key` header. Get one at https://muapi.ai/access-keys.

### 1. Submit a job

```http
POST https://api.muapi.ai/api/v1/gemini-video-vision
Content-Type: application/json
x-api-key: YOUR_API_KEY
```

**Minimum (required only):**

```json
{
  "prompt": "<prompt>",
  "video_url": "https://example.com/your-video_url"
}
```

**Full example (all params):**

```json
{
  "model": "gemini-2.5-flash",
  "prompt": "<prompt>",
  "video_url": "https://example.com/your-video_url",
  "system_prompt": "<system_prompt>"
}
```

**Response:**

```json
{
  "request_id": "abc123",
  "status": "processing"
}
```

### 2. Poll for the result

```http
GET https://api.muapi.ai/api/v1/predictions/{request_id}/result
x-api-key: YOUR_API_KEY
```

Possible `status` values: `queued`, `pending`, `processing`, `completed`, `failed`, `cancelled`. Poll every 2-5 seconds until terminal. When `completed`, the result URLs are in the `outputs` array.

**Example response when `completed`:**

```json
{
  "id": "abc123",
  "status": "completed",
  "outputs": [
    "https://cdn.muapi.ai/.../output.png"
  ],
  "urls": {
    "get": "https://api.muapi.ai/api/v1/predictions/abc123/result"
  },
  "created_at": "2026-05-08T12:34:56Z",
  "has_nsfw_contents": []
}
```

### cURL

```bash
# 1. Submit
REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/gemini-video-vision \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>","video_url":"https://example.com/your-video_url"}' | jq -r .request_id)

# 2. Poll until completed
while :; do
  RESP=$(curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY")
  STATUS=$(echo "$RESP" | jq -r .status)
  [ "$STATUS" = "completed" ] && echo "$RESP" | jq .outputs && break
  [ "$STATUS" = "failed" ] && echo "$RESP" && exit 1
  sleep 3
done
```

### Python

```python
import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/gemini-video-vision", headers=headers, json={"prompt":"<prompt>","video_url":"https://example.com/your-video_url"})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error")); 
    time.sleep(3)
```

## Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _optional_):
  Gemini model to use for video understanding. gemini-2.5-pro was removed from this enum after Google deprecated it for new users (returns a 404 NOT_FOUND); gemini-2.5-flash is the only currently supported option.
  - Default: `"gemini-2.5-flash"`
  - Options: `"gemini-2.5-flash"`

- **`prompt`** (`string`, _required_):
  The question or instruction describing what to analyze in the video.

- **`video_url`** (`string`, _required_):
  URL of the video to analyze.

- **`system_prompt`** (`string`, _optional_):
  Optional system-level instruction to guide the model's analysis style.

## Output Schema

The polling endpoint returns the following fields:

- **`id`** (`string`): The request ID.
- **`status`** (`string`): One of `queued`, `pending`, `processing`, `completed`, `failed`, `cancelled`.
- **`outputs`** (`array`): URLs to generated images/videos/audio. Empty until `status` is `completed`.
- **`urls.get`** (`string`): Self-link to re-fetch this prediction.
- **`error`** (`string` | `null`): Error message if `status` is `failed`.
- **`created_at`** (`string`): ISO-8601 timestamp of when the request was created.
- **`has_nsfw_contents`** (`array of boolean`): Per-output NSFW detection flags.

## Webhooks (optional)

Append `?webhook=https://your-server/path` to the submit URL. When the job reaches a terminal state, MuApi will POST the same shape as the polling response to your URL — no polling needed.

## Agent Integration

MuApi ships an MCP server and CLI so agents (Claude Code, Cursor, custom) can call this endpoint without writing HTTP code:

```bash
# Install the CLI
npm install -g muapi-cli

# Authenticate once
muapi auth login

# Expose all MuApi models as MCP tools to your agent
muapi mcp serve
```

The MCP server exposes tools that wrap submit + poll for every model, including `gemini-video-vision`. See `muapi --help` for category-specific shortcuts (`muapi image generate`, `muapi video from-image`, etc.).

## Related Models
- [Boost Style](https://muapi.ai/playground/suno-boost-music-style)
- [Claude Sonnet 4.6](https://muapi.ai/playground/claude-sonnet-4-6)
- [GPT5 Nano Text](https://muapi.ai/playground/gpt-5-nano)
- [Gemini 3.7 Flash (OpenAI)](https://muapi.ai/playground/gemini-3-7-flash-openai)
- [Suno Lyrics](https://muapi.ai/playground/suno-generate-lyrics)
- [Claude Opus 4.6](https://muapi.ai/playground/claude-opus-4-6)
- [GPT Codex](https://muapi.ai/playground/gpt-codex)
- [Claude Opus 4.8](https://muapi.ai/playground/claude-opus-4-8)
- [Gemini 3.5 Flash](https://muapi.ai/playground/gemini-3-5-flash)
- [Gemini 3.5 Flash (OpenAI)](https://muapi.ai/playground/gemini-3-5-flash-openai)
- [Claude Opus 4.7](https://muapi.ai/playground/claude-opus-4-7)
- [Gemini 3.1 Pro](https://muapi.ai/playground/gemini-3-1-pro)

## Resources
- [Playground Page](https://muapi.ai/playground/gemini-video-vision)
- [API Reference](https://muapi.ai/playground/gemini-video-vision?tab=2)
- [Global llms.txt](https://muapi.ai/llms.txt)