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
DeepSeekFrontier

DeepSeek V4 Pro

DeepSeek's large V4 Pro model: text-only through the API, with a 1M-token context, tool calls and selectable thinking effort; the weights are MIT-licensed.

Strengths

  • 1M-token context, up to 384K output
  • Thinking effort low, high or max
  • Tool calls and JSON output
  • Open weights under MIT

Best For

  • Code agents
  • Tool use and task automation

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.

DeepSeek · type: "deepseek"

Model ids: deepseek-v4-pro

1. Store the credential

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

${vault:deepseek-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": "deepseek",
      "parameters": {
        "apiKey": "${vault:deepseek-key}",
        "modelName": "deepseek-v4-pro",
        "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 deepseek-v4-pro agent",
  systemPrompt: "You are a helpful assistant.",
  provider: "deepseek",
  model: "deepseek-v4-pro",
  apiKey: "${vault:deepseek-key}"
)

Notes for EDDI

  • This provider requires the model's reasoning to be sent back during tool loops. EDDI's preset does it for you: leave returnThinking and sendThinking at their defaults.

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 ↗