OpenClaw
Set up OpenClaw with a custom OpenAI-compatible GetVibe API provider and the GETVIBE_API_KEY environment variable.
Ready-made config
Built from our catalog on request: the API address, every published model with its context and output limit, and the recommended settings. It contains no key. OpenClaw substitutes the key from GETVIBE_API_KEY (${GETVIBE_API_KEY}). models.mode: merge adds the provider next to yours.
# macOS / Linux
mkdir -p ~/.openclaw
curl -fsSL https://getvibeapi.com/api/integrations/openclaw.json -o ~/.openclaw/openclaw.json# Windows PowerShell
New-Item -ItemType Directory -Force "$HOME\.openclaw" | Out-Null
Invoke-WebRequest https://getvibeapi.com/api/integrations/openclaw.json -OutFile "$HOME\.openclaw\openclaw.json"- Main model —
gpt-6.1-sol: strong agentic coder with a large context at a moderate price; the bare id keeps cross-channel failover on. - Small tasks —
deepseek-v4.1-flash: cheapest capable model with a 1M context, for titles, summaries, commit messages and compaction. - Streaming on, a 600-second request timeout, reasoning effort medium: a long reasoning answer takes minutes, and without streaming it runs into the wait limit.
- Bare model IDs everywhere, no :suffix — that keeps automatic failover to a healthy channel on.
The catalog changes: when new models appear, download the file again. To keep only some models, add
?models= with comma-separated IDs to the URL.OpenClaw connects through the OpenAI-compatible Chat Completions. Do not pick OAuth/Codex subscription: that mode ignores its own Base URL.
Model setup
| Parameter | Type | Description |
|---|---|---|
Provider | select | OpenAI / OpenAI-compatible |
Base URL | field | https://getvibeapi.com/v1 |
API key | field | Your sk-pv-… key from the dashboard — the key itself, not a variable name |
Model | field | gpt-6.1-sol |
Verify
Save the connection, pick gpt-6.1-sol and send a short message. Other available ids are in the catalog.