Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.cowagent.ai/llms.txt

Use this file to discover all available pages before exploring further.

Option 1: Native integration (recommended): 
{
  "model": "ernie-5.0",
  "qianfan_api_key": "",
  "qianfan_api_base": "https://qianfan.baidubce.com/v2"
}
ParameterDescription
modelDefault recommendation: ernie-5.0; also supports ernie-x1.1, ernie-4.5-turbo-128k, ernie-4.5-turbo-32k
qianfan_api_keyQianfan API key, usually starting with bce-v3/
qianfan_api_baseOptional, defaults to https://qianfan.baidubce.com/v2

​
Model Selection

ModelUse Case
ernie-5.0Default recommendation; latest ERNIE flagship with the strongest overall capability
ernie-x1.1Deep-thinking reasoning model with lower hallucination and stronger instruction following / tool calling
ernie-4.5-turbo-128kLong-context and general chat
ernie-4.5-turbo-32kGeneral chat with a balanced context window and cost

​
Vision tool

Once qianfan_api_key is configured, Agent mode can auto-discover Qianfan for the Vision tool:
  • When the main model itself is multimodal (e.g. ernie-5.0, ernie-x1.1, ernie-4.5-turbo-vl), images are handled directly by the main model with no extra setup.
  • When the main model is text-only (e.g. ernie-4.5-turbo-128k), the Vision tool automatically falls back to ernie-4.5-turbo-vl.
To force a specific Vision model, set it explicitly in config.json: 
{
  "tool": {
    "vision": {
      "model": "ernie-4.5-turbo-vl"
    }
  }
}
Option 2: OpenAI-compatible configuration: 
{
  "model": "ernie-5.0",
  "bot_type": "openai",
  "open_ai_api_key": "",
  "open_ai_api_base": "https://qianfan.baidubce.com/v2"
}
Prefer qianfan_api_key for new configurations. Existing wenxin, wenxin-4, baidu_wenxin_api_key, and baidu_wenxin_secret_key configurations remain supported.