OpenClaw
OpenClaw is a personal agent that runs on your machine and can be reached from chat apps. Give it Inferray as a model provider.
Add the provider
Export a key:
export INFERRAY_API_KEY="inferray_..."
Merge this into ~/.openclaw/openclaw.json, with values for the model you choose from the catalogue:
{
"models": {
"mode": "merge",
"providers": {
"inferray": {
"baseUrl": "https://api.inferray.com/v1",
"apiKey": "${INFERRAY_API_KEY}",
"api": "openai-completions",
"models": [
{ "id": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6", "contextWindow": 1000000, "maxTokens": 64000 }
]
}
}
},
"agents": {
"defaults": {
"model": { "primary": "inferray/claude-sonnet-4-6" }
}
}
}
inferray/ in primary names the provider entry above; the id inside it is the model ID sent to Inferray.
Check it worked
Run one agent turn in a small project you don't mind it changing:
openclaw agent exec --cwd . "Read the README and summarise it in three bullet points."
Review what the agent did, then connect chat channels. Limit which tools the agent may use and who can message it before you expose it to incoming messages.
Models that work well here
- Claude Opus 5.5$4 in · $20 out per 1M tokens
- Claude Sonnet 5.5$2 in · $10 out per 1M tokens
- GPT-6.1 Sol$2 in · $10 out per 1M tokens
- Gemini 4 Argon$4 in · $20 out per 1M tokens
- Kimi K3$3 in · $15 out per 1M tokens
- GLM-5.3$0.77 in · $2.42 out per 1M tokens
- Gemini 3.8 Flash$0.75 in · $3.75 out per 1M tokens
- DeepSeek V4.1 Flash$0.15 in · $0.6 out per 1M tokens
- Run it on a Token Plan$20 a month buys $60 of usage across these models, with no 5-hour windows or weekly caps.