Skip to content
🚀 EDDI 6.5.0

19 LLM providers, knowledge bases that crawl your site and read your files, and conversations that follow compatible agent versionsWhat's new

Managed Cloud Get Started
All models
MetaOpen weights

Llama 4 (Scout, Maverick)

Meta's natively multimodal mixture-of-experts models with 17B active parameters: Scout (109B total) and Maverick (400B total).

Strengths

  • Text and image input
  • Mixture-of-experts efficiency
  • 12 languages
  • Long context (1M for Maverick on Bedrock)

Best For

  • Multimodal assistants
  • Visual reasoning
  • Long documents

Run It in EDDI

The fastest route is the Manager: open the agent wizard or the Platform Operator and pick the provider and model. To configure it yourself, follow these steps for the provider you want.

Amazon Bedrock · type: "bedrock"

Model ids: us.meta.llama4-maverick-17b-instruct-v1:0

1. Store the credential

This provider does not use an API key: Amazon Bedrock authenticates through the AWS credential chain: environment variables, an IAM role, or ~/.aws/credentials.

2. Configure the LLM task

Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.

{
  "tasks": [
    {
      "actions": [
        "send_message"
      ],
      "id": "chat",
      "type": "bedrock",
      "parameters": {
        "modelId": "us.meta.llama4-maverick-17b-instruct-v1:0",
        "region": "us-east-1",
        "maxTokens": "16384",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Oracle OCI Generative AI · type: "oracle-genai"

Model ids: meta.llama-4-maverick-17b-128e-instruct-fp8

1. Store the credential

This provider does not use an API key: OCI Generative AI authenticates with an OCI config profile from ~/.oci/config. Set compartmentId for your tenancy.

2. Configure the LLM task

Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.

{
  "tasks": [
    {
      "actions": [
        "send_message"
      ],
      "id": "chat",
      "type": "oracle-genai",
      "parameters": {
        "modelName": "meta.llama-4-maverick-17b-128e-instruct-fp8",
        "compartmentId": "ocid1.compartment.oc1..your-compartment",
        "configProfile": "DEFAULT",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Notes for EDDI

  • Some Bedrock models, including Llama 4 Maverick, are only reachable through a cross-region inference profile such as us.meta.llama4-maverick-17b-instruct-v1:0.

Related Models

Sources

The facts on this page come from the vendor's documentation, checked on 2026-09-30. Models change quickly, so confirm limits with the vendor before you rely on them. Prices are not listed here: see the vendor's pricing page.

Vendor documentation ↗