Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-23 | ✗→✓ | ▲ Improved | — | — |
| case-11 | ✗→✓ | ▲ Improved | — | — |
Configures OpenClaw to use free AI models from OpenRouter. Sets the best free model as primary, adds ranked fallbacks so rate limits don't interrupt the user, and preserves existing config.
Before running any FreeRide command, ensure:
echo $OPENROUTER_API_KEY. If empty, the user must get a free key at https://openrouter.ai/keys and set it:bash export OPENROUTER_API_KEY="sk-or-v1-..." # Or persist it: openclaw config set env.OPENROUTER_API_KEY "sk-or-v1-..."
freeride CLI is installed. Check with which freeride. If not found:bash cd ~/.openclaw/workspace/skills/free-ride pip install -e .
When the user wants free AI, run these steps in order:
bash# Step 1: Configure best free model + fallbacks freeride auto # Step 2: Restart gateway so OpenClaw picks up the changes openclaw gateway restart
That's it. The user now has free AI with automatic fallback switching.
Verify by telling the user to send /status to check the active model.
| Command | When to use it | |---------|----------------| | freeride auto | User wants free AI set up (most common) | | freeride auto -f | User wants fallbacks but wants to keep their current primary model | | freeride auto -c 10 | User wants more fallbacks (default is 5) | | freeride list | User wants to see available free models | | freeride list -n 30 | User wants to see all free models | | freeride switch <model> | User wants a specific model (e.g. freeride switch qwen3-coder) | | freeride switch <model> -f | Add specific model as fallback only | | freeride status | Check current FreeRide configuration | | freeride fallbacks | Update only the fallback models | | freeride refresh | Force refresh the cached model list |
After any command that changes config, always run openclaw gateway restart.
FreeRide updates only these keys in ~/.openclaw/openclaw.json:
agents.defaults.model.primary — e.g. openrouter/qwen/qwen3-coder:freeagents.defaults.model.fallbacks — e.g. ["openrouter/free", "nvidia/nemotron:free", ...]agents.defaults.models — allowlist so /model command shows the free modelsEverything else (gateway, channels, plugins, env, customInstructions, named agents) is preserved.
The first fallback is always openrouter/free — OpenRouter's smart router that auto-picks the best available model based on the request.
For auto-rotation when rate limited, the user can run:
bashfreeride-watcher --daemon # Continuous monitoring freeride-watcher --rotate # Force rotate now freeride-watcher --status # Check rotation history
| Problem | Fix | |---------|-----| | freeride: command not found | cd ~/.openclaw/workspace/skills/free-ride && pip install -e . | | OPENROUTER_API_KEY not set | User needs a key from https://openrouter.ai/keys | | Changes not taking effect | openclaw gateway restart then /new for fresh session | | Agent shows 0 tokens | Check freeride status — primary should be openrouter/<provider>/<model>:free |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +78 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.