# Generate images, video and audio in coding agents

> Generate images, video and audio from Codex, Claude Code, Cursor or Cline. Keep a text model as the main model and call media models through BigModel.io's MCP server (https://bigmodel.io/mcp) or an AGENTS.md note.

Web version: https://bigmodel.io/docs/agent-media · Updated 2026-10-20

A coding agent's **main model must be a text model**: it has to chat and call tools. Image, video and audio models only produce content, so they cannot be the main model; picking one in the model selector fails.

Instead, let the text model **call** the media models. Two ways:

| Way | How | For |
|---|---|---|
| **MCP server (recommended)** | Add `https://bigmodel.io/mcp` to the agent; it gains tools such as `generate_image` and `generate_video` | Tools that support MCP: Codex, Claude Code, Cursor, Cline, Cherry Studio and more |
| **AGENTS.md note** | Describe the endpoints and commands in the project instructions; the agent runs `curl` itself | Agents that run commands but where MCP is inconvenient |

Both use your own API key and are billed exactly like the API: images per image, video per second, audio per request or duration. Prices are on the [models page](https://bigmodel.io/models).

## Way 1: MCP server

The server is `https://bigmodel.io/mcp` and authenticates with your API key (`Authorization: Bearer <your key>`). Set `BIGMODEL_API_KEY` in your shell first.

### Codex

Add to `~/.codex/config.toml`:

```toml
[mcp_servers.bigmodel]
url = "https://bigmodel.io/mcp"
bearer_token_env_var = "BIGMODEL_API_KEY"
tool_timeout_sec = 300
```

Videos usually take 1–3 minutes; a longer `tool_timeout_sec` lets the tool wait for the result.

### Claude Code

```bash
claude mcp add --transport http bigmodel https://bigmodel.io/mcp \
  --header "Authorization: Bearer $BIGMODEL_API_KEY"
```

### Cursor

Add to `~/.cursor/mcp.json` (or `.cursor/mcp.json` in the project):

```json
{
  "mcpServers": {
    "bigmodel": {
      "url": "https://bigmodel.io/mcp",
      "headers": { "Authorization": "Bearer ${env:BIGMODEL_API_KEY}" }
    }
  }
}
```

Other tools that support Streamable HTTP MCP servers take the same URL and header.

### Tools

| Tool | What it does |
|---|---|
| `list_media_models` | Lists the image, video and audio models you can use, with prices; call it first |
| `generate_image` | Makes 1–4 images from a prompt and returns links |
| `generate_video` | Makes a video, optionally from a start image; waits up to `wait_seconds` (default 50, max 240) and otherwise returns the task ID |
| `get_video` | Checks a video task and returns the link when done |
| `generate_audio` | Makes music or sound; model-specific fields go in `options` |
| `get_audio` | Checks an audio task |

Links are valid for 24 hours. Have the agent download them into the project with `curl -L -o <file> <link>`, for example:

> Use BigModel to make a 1024x1024 flat-illustration app icon and download it to `assets/icon.png`.

## Way 2: AGENTS.md note

Put this in `AGENTS.md` at the project root (`CLAUDE.md` for Claude Code); the agent runs the commands itself.

````markdown
## Generating images, video and audio

Use BigModel.io. The key is in the environment variable `BIGMODEL_API_KEY`; never write it into code or commit it.
Result links are valid for 24 hours: download them into the project right away.

- Models: `curl -s "https://bigmodel.io/v1/models?type=all" -H "Authorization: Bearer $BIGMODEL_API_KEY"`; use models whose `architecture.modality` is image, video or audio.
- Image (returns when done):
  ```bash
  curl -s https://bigmodel.io/v1/images/generations \
    -H "Authorization: Bearer $BIGMODEL_API_KEY" -H "Content-Type: application/json" \
    -d '{"model":"<image model>","prompt":"<description>","size":"1024x1024","n":1}'
  ```
  Download `data[0].url`: `curl -L -o assets/<name>.png "<url>"`.
- Video (async task):
  ```bash
  curl -s https://bigmodel.io/v1/videos \
    -H "Authorization: Bearer $BIGMODEL_API_KEY" -H "Content-Type: application/json" \
    -d '{"model":"<video model>","prompt":"<description>","seconds":5}'
  ```
  Poll `GET https://bigmodel.io/v1/videos/<id>` every 10 seconds until `status` is `succeeded`, then download `output.url`. `failed` is not charged.
- Audio (async task): `POST https://bigmodel.io/v1/audio/generations`, used like video; poll `GET /v1/audio/generations/<id>`.
- Tell me the estimated cost before generating (prices: https://bigmodel.io/models); ask me first if it is over $1.
````

## Troubleshooting

**Picked an image or video model in the model selector and got `model_endpoint_mismatch`.** Switch the main model back to a text model and use the tools above for media.

**The MCP tools return 401.** The agent did not get `BIGMODEL_API_KEY`, or the header does not carry the key.

**The video stays "still running".** Videos can take a few minutes. Ask the agent to call `get_video` later, or raise `wait_seconds` and the tool timeout.

**Insufficient balance.** Video is billed per second and the balance has to cover the estimate when you submit. [Top up](https://bigmodel.io/purchase).

## Related

- [Image generation](https://bigmodel.io/docs/image-generation), [Video generation](https://bigmodel.io/docs/video-generation), [Audio generation](https://bigmodel.io/docs/audio-generation)
- [Codex](https://bigmodel.io/docs/codex-cli), [Claude Code](https://bigmodel.io/docs/claude-code), [Cursor](https://bigmodel.io/docs/cursor)
- [Multimodal overview](https://bigmodel.io/docs/multimodal-overview)