#How to change model
1 messages ยท Page 1 of 1 (latest)
no idea, but don't go for Gemini anyways, it's currently bugged from what I'm seeing
here you go with the model change steps
no idea, I'm going to try openai now
thx
please lemme know if openrouter works if you give it a try :)
PowerShell: Same commands, just run in PowerShell terminal:
clawdbot configure
# or
clawdbot onboard --auth-choice openrouter-api-key
clawdbot models set openrouter/<model-name>
OpenRouter: Yes! It's supported. Just get your API key from https://openrouter.ai/keys, then run:
clawdbot onboard --auth-choice openrouter-api-key --openrouter-api-key YOUR_KEY
# or use configure wizard
clawdbot configure
Popular OpenRouter models include:
openrouter/google/gemini-2.0-flash-expopenrouter/openai/gpt-4oopenrouter/anthropic/claude-opus-4-5openrouter/deepseek/deepseek-chat
Set it with: clawdbot models set openrouter/<model>
Based on the docs, here's how to change your model provider:
Quick method - run the configure wizard:
clawdbot configure
This is an interactive wizard that walks you through models, channels, skills, and gateway config.
Or set it up via the onboarding command:
clawdbot onboard --auth-choice <provider>
Valid provider options include:
openai-api-keyanthropic-api-keyopenrouter-api-key
Am I able to use my anthropic max subscription?
moonshot-api-keygemini-api-keyzai-api-keyminimax-apiopencode-zen
Then set your default model:
clawdbot models set <provider>/<model>
# Example: clawdbot models set anthropic/claude-opus-4-5
Docs reference: https://docs.moltbot.ai/cli (see configure, onboard, and models sections)
doesnt work
open router not work for me too
can someone suggest free llm please, i want it just for test
yea me too, let me know if you find
yeah sure
I can't get gpt to work either omfg
โ ๏ธ Agent failed before reply: No API key found for provider "openai". You are authenticated with OpenAI Codex OAuth. Use openai-codex/gpt-5.2 (ChatGPT OAuth) or set OPENAI_API_KEY for openai/gpt-5.2.
Logs: openclaw logs --follow
Free options for testing:
-
Groq (fast, great free tier):
clawdbot onboard --auth-choice groq-api-key clawdbot models set groq/llama-3.3-70b-versatile -
Google Gemini Free:
clawdbot onboard --auth-choice gemini-api-key clawdbot models set google/gemini-2.0-flash-exp -
OpenRouter Free Models (no API key needed for some):
clawdbot configure # select OpenRouter, choose free model
clawdbot models set openrouter/google/gemini-2.0-flash-exp
My pick for testing: Groq is fastest and easiest to set up.
managed to get openrouter working, did onboard procedure with full reset i think that helped
I switched to openai and Seller of Souls
APL.
โ 01:00
You have hit your ChatGPT usage limit (go plan).
WTF.
This is likely a billing/usage limit on your OpenAI API key, not Clawdbot. Common issues:
Check your OpenAI account:
- Go to https://platform.openai.com/usage
- Make sure you have API credits, not just ChatGPT Plus subscription
ChatGPT Plus โ OpenAI API - they're separate billing. To use OpenAI via API, you need to buy API credits.
Better free options for testing:
-
Groq (truly free, no limits):
clawdbot onboard --auth-choice groq-api-key clawdbot models set groq/llama-3.3-70b-versatile -
OpenRouter Free (some models are free):
clawdbot onboard --auth-choice openrouter-api-key
clawdbot models set openrouter/deepseek/deepseek-chat
- Google Gemini Free (generous free tier):
clawdbot onboard --auth-choice gemini-api-key clawdbot models set google/gemini-2.0-flash-exp
Recommendation: Try Groq - it's fast and genuinely free for testing.
I used OAuth. And Usage shows 0 rquests
@slow pasture which operrouter you chose?
Hey @slow pasture โ which OpenRouter model did you choose? ๐ฆ
Asked them for you! Let's see what they picked. ๐ฆ