Faster OpenClaw in APAC. One config change.
Keep your OpenClaw workflow exactly the same. Point `models.providers` to Brightnode's OpenAI-compatible Singapore endpoint and your Telegram/WhatsApp/Slack agent replies faster with lower token costs.
Why switch your OpenClaw provider to Brightnode
- Your OpenClaw agent responds faster in APAC. Brightnode routes from Singapore with sub-100ms benchmark TTFT.
- Transparent per-token pricing across proprietary and Brightnode-hosted models, shown directly in the catalog.
- No workflow changes. Brightnode is OpenAI-compatible, so you drop it into models.providers and restart OpenClaw.
Copy this config. Restart. Done.
OpenClaw supports custom providers through `models.providers`. Add Brightnode, keep `api: "openai-completions"`, and set your default model as `brightnode/<model-id>`.
Example openclaw.json
{
"env": {
"BRIGHTNODE_API_KEY": "your-brightnode-api-key"
},
"agents": {
"defaults": {
"model": {
"primary": "brightnode/meta-llama/Llama-3.3-70B-Instruct"
},
"models": {
"brightnode/meta-llama/Llama-3.3-70B-Instruct": {}
}
}
},
"models": {
"mode": "merge",
"providers": {
"brightnode": {
"baseUrl": "https://api.brightnode.cloud/v1",
"apiKey": "${BRIGHTNODE_API_KEY}",
"api": "openai-completions",
"models": [
{
"id": "meta-llama/Llama-3.3-70B-Instruct",
"name": "Llama 3.3 70B Instruct"
}
]
}
}
}
}Quick sanity check:
curl https://api.brightnode.cloud/v1/chat/completions \
-H "Authorization: Bearer $BRIGHTNODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"meta-llama/Llama-3.3-70B-Instruct","messages":[{"role":"user","content":"ping"}]}'Restart OpenClaw after saving config:
openclaw gateway run
Most common OpenClaw model picks on Brightnode
These are the most common model choices OpenClaw users run through Brightnode.
| Model | Input / 1M | Output / 1M | Context | Latency (Singapore) |
|---|---|---|---|---|
| Claude Sonnet 4.5 | $3.00 | $15.00 | 200,000 | 40ms (Singapore) |
| Claude Sonnet 4 | $3.00 | $15.00 | 200,000 | 83ms (Singapore) |
| DeepSeek V3.2 | $0.74 | $2.22 | 131,072 | 40ms (Singapore) |
| Kimi K2.5 | $0.72 | $3.60 | 131,072 | 40ms (Singapore) |
| Llama 3.3 70B Instruct | $0.22 | $0.50 | 131,072 | 27ms (Singapore) |
Plus many more models are available on the Brightnode models page.
8.9x faster than global routers
3.7x faster at 200 token output
Global routers: 3.3% error rate
Consistent under parallel load
Ready to speed up your OpenClaw agent
Get your API key and switch providers in 5 minutes.
Keep your current OpenClaw setup, paste the provider block, and ship faster replies to your users in APAC.