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
AlibabaFrontier

Qwen 3.8 (Max, Flash)

Alibaba's Qwen 3.8 line: Max is the flagship, and Max and Flash both offer a 1M-token context, image and video input and hybrid thinking.

Strengths

  • 1M-token context, 131K output
  • Text, image and video input
  • Function calling and structured outputs
  • Regions include Frankfurt and Virginia

Best For

  • Long-horizon coding
  • Professional work in law, finance and design
  • Multimodal agents

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.

Alibaba Cloud Model Studio · type: "qwen"

Model ids: qwen3.8-max, qwen3.8-flash

1. Store the credential

Add the provider's API key to the Secrets Vault in the Manager, or with PUT /secretstore/secrets/default/qwen-key, under the name used below. Configurations reference it as ${vault:…}, so the key never appears in plain text.

${vault:qwen-key}

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": "qwen",
      "parameters": {
        "apiKey": "${vault:qwen-key}",
        "modelName": "qwen3.8-max",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Or create the whole agent in one call

setup_agent writes the rules, LLM configuration and workflow, then deploys the agent. Call it over MCP or POST /administration/agents/setup.

setup_agent(
  agentName: "My qwen3.8-max agent",
  systemPrompt: "You are a helpful assistant.",
  provider: "qwen",
  model: "qwen3.8-max",
  apiKey: "${vault:qwen-key}"
)

Groq · type: "groq"

Model ids: qwen/qwen3.8-27b

1. Store the credential

Add the provider's API key to the Secrets Vault in the Manager, or with PUT /secretstore/secrets/default/groq-key, under the name used below. Configurations reference it as ${vault:…}, so the key never appears in plain text.

${vault:groq-key}

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": "groq",
      "parameters": {
        "apiKey": "${vault:groq-key}",
        "modelName": "qwen/qwen3.8-27b",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Or create the whole agent in one call

setup_agent writes the rules, LLM configuration and workflow, then deploys the agent. Call it over MCP or POST /administration/agents/setup.

setup_agent(
  agentName: "My qwen/qwen3.8-27b agent",
  systemPrompt: "You are a helpful assistant.",
  provider: "groq",
  model: "qwen/qwen3.8-27b",
  apiKey: "${vault:groq-key}"
)

Notes for EDDI

  • Pick a region with "region": "intl", "cn" or "us". For a workspace-specific Alibaba host, set baseUrl instead.
  • Groq marks some models, including qwen3.8-27b, as Preview: for evaluation, and possibly withdrawn at short notice.

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 ↗ · Pricing ↗