Generate AI chat responses

Usage example

{
  "steps": {
    "reply": {
      "robot": "/ai/chat",
      "model": "auto",
      "messages": "Summarize this in one sentence: Transloadit handles uploads and media processing."
    }
  }
}

Parameters

• interpolate

  boolean | Record<string, boolean>

  Controls whether Assembly Variables are interpolated for individual instruction fields.

  By default, most Robot instruction fields interpolate Assembly Variables. Set this to false to treat every instruction field as literal text, or set an individual field path to false to treat only that field as literal text. For Robot-specific fields that are literal by default, set this to true or set that field path to true to opt back into interpolation.

  Use field names such as path, or dotted paths such as ffmpeg.vf for nested objects.

• output_meta

  Record<string, boolean> | boolean | Array<string>

  Allows you to specify a set of metadata that is more expensive on CPU power to calculate, and thus is disabled by default to keep your Assemblies processing fast.

  For images, you can add "has_transparency": true in this object to extract if the image contains transparent parts and "dominant_colors": true to extract an array of hexadecimal color codes from the image.

  For images, you can also add "blurhash": true to extract a BlurHash string — a compact representation of a placeholder for the image, useful for showing a blurred preview while the full image loads.

  For videos, you can add the "colorspace: true" parameter to extract the colorspace of the output video.

  For videos, you can also add "interlaced": true to detect whether the video is interlaced. This combines the cheap ffprobe field_order flag with a bounded idet sampling pass over the first frames of the source, exposing interlaced, field_order, and a diagnostic interlace_detection object under file.meta. This is computationally expensive and billed accordingly.

  For audio, you can add "mean_volume": true to get a single value representing the mean average volume of the audio file.

  You can also set this to false to skip metadata extraction and speed up transcoding.

• result

  boolean (default: false)

  Whether the results of this Step should be present in the Assembly Status JSON

• queue

  batch

  Setting the queue to 'batch', manually downgrades the priority of jobs for this step to avoid consuming Priority job slots for jobs that don't need zero queue waiting times

• force_accept

  boolean (default: false)

  Force a Robot to accept a file type it would have ignored.

  By default, Robots ignore files they are not familiar with. 🤖/video/encode, for example, will happily ignore input images.

  With the force_accept parameter set to true, you can force Robots to accept all files thrown at them. This will typically lead to errors and should only be used for debugging or combatting edge cases.

• ignore_errors

  boolean | Array<meta | execute> (default: [])

  Ignore errors during specific phases of processing.

  Setting this to ["meta"] will cause the Robot to ignore errors during metadata extraction.

  Setting this to ["execute"] will cause the Robot to ignore errors during the main execution phase.

  Setting this to true is equivalent to ["meta", "execute"] and will ignore errors in both phases.

• use

  string | Array<string> | Array<object> | object

  Specifies which Step(s) to use as input.

  • You can pick any names for Steps except ":original" (reserved for user uploads handled by Transloadit)
  • You can provide several Steps as input with arrays:
    

    {
      "use": [
        ":original",
        "encoded",
        "resized"
      ]
    }
    

  • You can also tag an input Step with as to pass semantic intent to robots:
  • You can also tag input Steps with as to pass semantic intent to robots:
    

    {
      "use": [
        {
          "name": ":original",
          "as": "image"
        },
        {
          "name": ":original",
          "as": "mask"
        }
      ]
    }
    

  Tip

  That's likely all you need to know about use, but you can view Advanced use cases.

• model

  string | "auto" (default: "auto")

  The model to use. Transloadit can pick the best model for the job if you set this to "auto".

• schema

  string

  The JSON Schema that the LLM should output

• messages — required

  string | Array<object>

  The prompt, or message history to send to the LLM.

• system_message

  string

  Set the system/developer prompt, if the model allows it. If this prompt contains literal documentation or code examples with ${...} syntax, set interpolate.system_message to false.

• reasoning_effort

  xhigh | high | medium | low

  Controls how much effort the model spends on reasoning. Higher values produce more thorough responses but cost more tokens. Applies to models that support extended thinking (OpenAI o-series, GPT-5.x, Anthropic Claude with thinking). If omitted, the model default is used.

• credentials

  string | Array<string>

  Names of template credentials to make available to the robot. When using your own AI provider keys, Transloadit charges a 10% markup (minimum $0.0005 per request).

• test_credentials

  boolean

  Use Transloadit-provided credentials for testing. Usage is billed at provider cost plus a 10% markup (minimum $0.0005 per request).

• mcp_servers

  Array<object>

  The MCP servers to use for tool calling. You can use any MCP server reachable from your environment. Use headers to pass server-specific auth (for example Authorization: Bearer <token>). For Transloadit's MCP server: Bearer tokens minted via /token satisfy Signature Authentication (signature checks apply only to key/secret requests). auth: "transloadit" is reserved for API2-managed auth to Transloadit-hosted MCP servers.