Oracle Cloud Infrastructure Documentation

xAI Grok 4.20 Multi-Agent

The xAI Grok 4.20 Multi-Agent model enables Realtime Multi-Agent Research to orchestrate multiple AI agents that work together in real time to perform deep, multi-step research tasks. Each agent specializes in a particular aspect of the research (searching the web, analyzing data, synthesizing findings) and they collaborate to deliver comprehensive, well-sourced answers.

xAI Documentation References

Regions for this Model

Important

For supported regions, endpoint types (on-demand or dedicated AI clusters), and hosting (OCI Generative AI or external calls) for this model, see the Models by Region page. For details about the regions, see the Generative AI Regions page.

Access this Model

Access this model in the supported regions through the API with the following endpoints:
https://inference.generativeai.us-ashburn-1.oci.oraclecloud.com/v1/responses
https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/v1/responses
https://inference.generativeai.us-phoenix-1.oci.oraclecloud.com/v1/responses
Note

This model isn't available in the Console.

Key Features

  • Model names in OCI Generative AI:
    • xai.grok-4.20-multi-agent-0309
    • xai.grok-4.20-multi-agent (an alias that points to xai.grok-4.20-multi-agent-0309)
  • Available On-Demand: Yes, only through the API.
  • Multimodal support: Input text and images and get a text output.
  • Context Length: 2 million tokens.
  • Function Calling: Yes, through the API.
  • Structured Outputs: Yes.

  • Cached Input Tokens: Yes

    Important note: The cached‑input feature is available in both the playground and the API. However, that information can only be retrieved through the API.

  • Knowledge Cutoff: Not available.

Limits

Tokens per minute (TPM)
For the TPM limit increase, use the following limit name: grok-4-2-multi-agent-tokens-per-minute-count (for 200,000 tokens). See Requesting a Service Limit Increase.
Image Inputs
  • API: Only JPG/JPEG and PNG file formats are supported. Submit a base64 encoded version of an image, ensuring that each converted image is more than 256 and less than 1,792 tokens. For example, a 512 x 512 image typically converts to around 1,610 tokens. There's no stated maximum number of images that can be uploaded. The combined token count for both text and images must be within the model's overall context window of 2 million tokens.

On-Demand Mode

Note

The Grok models are available only in the on-demand mode.
Model Name OCI Model Name
xAI Grok 4.20 Multi-Agent
  • xai.grok-4.20-multi-agent-0309
  • xai.grok-4.20-multi-agent