I can't add openrouter/free model in picoclaw

[shadmanshaikh]

ubuntu@ip-172-26-1-25:~/picoclaw$ picoclaw agent -m "hi"
2026/02/28 09:36:24 [2026-02-28T09:36:24Z] [INFO] agent: Created implicit main agent (no agents.list configured)
2026/02/28 09:36:24 [2026-02-28T09:36:24Z] [INFO] agent: Agent initialized {tools_count=14, skills_total=6, skills_available=6}
2026/02/28 09:36:24 [2026-02-28T09:36:24Z] [INFO] agent: Processing message from cli:cron: hi {channel=cli, chat_id=direct, sender_id=cron, session_key=cli:default}
2026/02/28 09:36:24 [2026-02-28T09:36:24Z] [INFO] agent: Routed message {agent_id=main, session_key=agent:main:main, matched_by=default}
2026/02/28 09:36:24 [2026-02-28T09:36:24Z] [ERROR] agent: LLM call failed {iteration=1, error=API request failed:
Status: 400
Body: {"error":{"message":"free is not a valid model ID","code":400},"user_id":"user_xxxxxxxxxxxxxxxx"}, agent_id=main}
Error: error processing message: LLM call failed after retries: API request failed:
Status: 400
Body: {"error":{"message":"free is not a valid model ID","code":400},"user_id":"user_xxxxxxxxx"}
Usage:
picoclaw agent [flags]

---

this is the config.json file setup :
"agents": {
"defaults": {
"workspace": "~/.picoclaw/workspace",
"restrict_to_workspace": true,
"model": "free",
"max_tokens": 32768,
"max_tool_iterations": 50
}
},
"providers":{
"openrouter" :{
"api_key" :"sk-or-v1-xxxxxxxxxxxxxxxx",
"api_base" :"https://openrouter.ai/api/v1"
}
},

[aptonline]

As per the error, the model you have chosen (free) is not a valid model name. Replace this with something like stepfun/step-3.5-flash:free

[shadmanshaikh]

If I use stepfun/step-3.5-flash:free as a model I get the following :

ubuntu@ip-172-26-1-25:~/picoclaw$ picoclaw agent -m "hi" --model stepfun/step-3.5-flash:free

Error: error creating provider: failed to create provider for model "stepfun/step-3.5-flash:free": unknown protocol "stepfun" in model "stepfun/step-3.5-flash:free"

[aptonline]

This works for me:

  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "restrict_to_workspace": true,
      "provider": "openrouter",
      "model": "stepfun/step-3.5-flash:free",
      "max_tokens": 200000,
      "temperature": 0.7,
      "max_tool_iterations": 20
    }
  }

[shadmanshaikh]

I'm getting :

ubuntu@ip-172-26-1-25:~/picoclaw$ picoclaw agent -m "hi"
Error: error creating provider: failed to create provider for model "stepfun/step-3.5-flash:free": unknown protocol "stepfun" in model "stepfun/step-3.5-flash:free"
Usage:

[aptonline]

paste your config again.

[tuantho]

Try to add prefix openrouter/

[DuckieYuckie]

Same problem here, new configuration from zero and I've tried aeverything but it just doesn't work. Here's my config (I've removed sensitive infos). I also tried "openrouter/stepfun/step-3.5-flash:free" in both agents default and model list. , I also tried a lot of different configs with and without openrouter/ as prefix, also tried as model name the name in the Openrouter page but nothing works

Error: error creating provider: model "stepfun/step-3.5-flash:free" not found in model_list: model "stepfun/step-3.5-flash:free" not found in model_list or providers

{
  "session": {
    "dm_scope": "per-channel-peer"
  },
  "agents": {
    "defaults": {
      "workspace": "~/.picoclaw/workspace",
      "restrict_to_workspace": true,
      "provider": "",
      "model": "stepfun/step-3.5-flash:free",
      "max_tokens": 32768,
      "max_tool_iterations": 50
    }
  },
  "channels": {
    "whatsapp": {
      "enabled": false,
      "bridge_url": "ws://localhost:3001",
      "use_native": false,
      "session_store_path": "",
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "telegram": {
      "enabled": true,
      "token": "",
      "proxy": "",
      "allow_from": [],
      "group_trigger": {},
      "typing": {
        "enabled": true
      },
      "placeholder": {
        "enabled": true,
        "text": "Thinking... 💭"
      },
      "reasoning_channel_id": ""
    },
    "feishu": {
      "enabled": false,
      "app_id": "",
      "app_secret": "",
      "encrypt_key": "",
      "verification_token": "",
      "allow_from": [],
      "group_trigger": {},
      "reasoning_channel_id": ""
    },
    "discord": {
      "enabled": false,
      "token": "",
      "allow_from": [],
      "mention_only": false,
      "group_trigger": {},
      "typing": {},
      "placeholder": {},
      "reasoning_channel_id": ""
    },
    "maixcam": {
      "enabled": false,
      "host": "0.0.0.0",
      "port": 18790,
      "allow_from": [],
      "reasoning_channel_id": ""
    },
    "qq": {
      "enabled": false,
      "app_id": "",
      "app_secret": "",
      "allow_from": [],
      "group_trigger": {},
      "reasoning_channel_id": ""
    },
    "dingtalk": {
      "enabled": false,
      "client_id": "",
      "client_secret": "",
      "allow_from": [],
      "group_trigger": {},
      "reasoning_channel_id": ""
    },
    "slack": {
      "enabled": false,
      "bot_token": "",
      "app_token": "",
      "allow_from": [],
      "group_trigger": {},
      "typing": {},
      "placeholder": {},
      "reasoning_channel_id": ""
    },
    "line": {
      "enabled": false,
      "channel_secret": "",
      "channel_access_token": "",
      "webhook_host": "0.0.0.0",
      "webhook_port": 18791,
      "webhook_path": "/webhook/line",
      "allow_from": [],
      "group_trigger": {
        "mention_only": true
      },
      "typing": {},
      "placeholder": {},
      "reasoning_channel_id": ""
    },
    "onebot": {
      "enabled": false,
      "ws_url": "ws://127.0.0.1:3001",
      "access_token": "",
      "reconnect_interval": 5,
      "group_trigger_prefix": [],
      "allow_from": [],
      "group_trigger": {},
      "typing": {},
      "placeholder": {},
      "reasoning_channel_id": ""
    },
    "wecom": {
      "enabled": false,
      "token": "",
      "encoding_aes_key": "",
      "webhook_url": "",
      "webhook_host": "0.0.0.0",
      "webhook_port": 18793,
      "webhook_path": "/webhook/wecom",
      "allow_from": [],
      "reply_timeout": 5,
      "group_trigger": {},
      "reasoning_channel_id": ""
    },
    "wecom_app": {
      "enabled": false,
      "corp_id": "",
      "corp_secret": "",
      "agent_id": 0,
      "token": "",
      "encoding_aes_key": "",
      "webhook_host": "0.0.0.0",
      "webhook_port": 18792,
      "webhook_path": "/webhook/wecom-app",
      "allow_from": [],
      "reply_timeout": 5,
      "group_trigger": {},
      "reasoning_channel_id": ""
    },
    "pico": {
      "enabled": false,
      "token": "",
      "ping_interval": 30,
      "read_timeout": 60,
      "write_timeout": 10,
      "max_connections": 100,
      "allow_from": [],
      "placeholder": {}
    }
  },
  "model_list": [
    {
      "model_name": "glm-4.7",
      "model": "zhipu/glm-4.7",
      "api_base": "https://open.bigmodel.cn/api/paas/v4",
      "api_key": ""
    },
    {
      "model_name": "gpt-5.2",
      "model": "openai/gpt-5.2",
      "api_base": "https://api.openai.com/v1",
      "api_key": ""
    },
    {
      "model_name": "claude-sonnet-4.6",
      "model": "anthropic/claude-sonnet-4.6",
      "api_base": "https://api.anthropic.com/v1",
      "api_key": ""
    },
    {
      "model_name": "deepseek-chat",
      "model": "deepseek/deepseek-chat",
      "api_base": "https://api.deepseek.com/v1",
      "api_key": ""
    },
    {
      "model_name": "gemini-2.0-flash",
      "model": "gemini/gemini-2.0-flash-exp",
      "api_base": "https://generativelanguage.googleapis.com/v1beta",
      "api_key": ""
    },
    {
      "model_name": "qwen-plus",
      "model": "qwen/qwen-plus",
      "api_base": "https://dashscope.aliyuncs.com/compatible-mode/v1",
      "api_key": ""
    },
    {
      "model_name": "moonshot-v1-8k",
      "model": "moonshot/moonshot-v1-8k",
      "api_base": "https://api.moonshot.cn/v1",
      "api_key": ""
    },
    {
      "model_name": "llama-3.3-70b",
      "model": "groq/llama-3.3-70b-versatile",
      "api_base": "https://api.groq.com/openai/v1",
      "api_key": ""
    },
    {
      "model_name": "step-3.5-flash:free",
      "model": "openrouter/stepfun/step-3.5-flash:free",
      "api_base": "https://openrouter.ai/api/v1",
      "api_key": ""
    },
    {
      "model_name": "openrouter-gpt-5.2",
      "model": "openrouter/openai/gpt-5.2",
      "api_base": "https://openrouter.ai/api/v1",
      "api_key": ""
    },
    {
      "model_name": "nemotron-4-340b",
      "model": "nvidia/nemotron-4-340b-instruct",
      "api_base": "https://integrate.api.nvidia.com/v1",
      "api_key": ""
    },
    {
      "model_name": "cerebras-llama-3.3-70b",
      "model": "cerebras/llama-3.3-70b",
      "api_base": "https://api.cerebras.ai/v1",
      "api_key": ""
    },
    {
      "model_name": "doubao-pro",
      "model": "volcengine/doubao-pro-32k",
      "api_base": "https://ark.cn-beijing.volces.com/api/v3",
      "api_key": ""
    },
    {
      "model_name": "deepseek-v3",
      "model": "shengsuanyun/deepseek-v3",
      "api_base": "https://api.shengsuanyun.com/v1",
      "api_key": ""
    },
    {
      "model_name": "gemini-flash",
      "model": "antigravity/gemini-3-flash",
      "api_key": "",
      "auth_method": "oauth"
    },
    {
      "model_name": "copilot-gpt-5.2",
      "model": "github-copilot/gpt-5.2",
      "api_base": "http://localhost:4321",
      "api_key": "",
      "auth_method": "oauth"
    },
    {
      "model_name": "llama3",
      "model": "ollama/llama3",
      "api_base": "http://localhost:11434/v1",
      "api_key": "ollama"
    },
    {
      "model_name": "mistral-small",
      "model": "mistral/mistral-small-latest",
      "api_base": "https://api.mistral.ai/v1",
      "api_key": ""
    },
    {
      "model_name": "local-model",
      "model": "vllm/custom-model",
      "api_base": "http://localhost:8000/v1",
      "api_key": ""
    }
  ],
  "gateway": {
    "host": "127.0.0.1",
    "port": 18790
  },
  "tools": {
    "web": {
      "brave": {
        "enabled": false,
        "api_key": "",
        "max_results": 5
      },
      "tavily": {
        "enabled": false,
        "api_key": "",
        "base_url": "",
        "max_results": 0
      },
      "duckduckgo": {
        "enabled": true,
        "max_results": 5
      },
      "perplexity": {
        "enabled": false,
        "api_key": "",
        "max_results": 5
      }
    },
    "cron": {
      "exec_timeout_minutes": 5
    },
    "exec": {
      "enable_deny_patterns": true,
      "custom_deny_patterns": null
    },
    "skills": {
      "registries": {
        "clawhub": {
          "enabled": true,
          "base_url": "https://clawhub.ai",
          "auth_token": "",
          "search_path": "",
          "skills_path": "",
          "download_path": "",
          "timeout": 0,
          "max_zip_size": 0,
          "max_response_size": 0
        }
      },
      "max_concurrent_searches": 2,
      "search_cache": {
        "max_size": 50,
        "ttl_seconds": 300
      }
    },
    "media_cleanup": {
      "enabled": true,
      "max_age_minutes": 30,
      "interval_minutes": 5
    }
  },
  "heartbeat": {
    "enabled": true,
    "interval": 30
  },
  "devices": {
    "enabled": false,
    "monitor_usb": true
  }
}

[LeandroPelegrini]

Running here with:

picoclaw agent --model step-3.5-flash:free

config:

{
      "model_name": "step-3.5-flash:free",
      "model": "openrouter/stepfun/step-3.5-flash:free",
      "api_base": "https://openrouter.ai/api/v1",
      "api_key": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
    }

you are setting the name "step-3.5-flash:free" and calling "stepfun/step-3.5-flash:free"

[DuckieYuckie]

Running here with:

picoclaw agent --model step-3.5-flash:free

config:

{
      "model_name": "step-3.5-flash:free",
      "model": "openrouter/stepfun/step-3.5-flash:free",
      "api_base": "https://openrouter.ai/api/v1",
      "api_key": "XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX"
    }

you are setting the name "step-3.5-flash:free" and calling "stepfun/step-3.5-flash:free"

This works 100%, thank you, and in "agents" you put "step-3.5-flash:free" as model

[DuckieYuckie]

Isn't it possible to add a multi model configuration with two or more models active at the same time? Or fallback models for when one model isn't reachable?