free-tier-ai-router
Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras plus any OpenAI-compatible endpoint (including local Ollama/llama.cpp/vLLM). Probes every model on every key, measures real quality and real published rate limits, t
as observed 2026-09-17T19:21:47.048Z- Identifier
free-tier-ai-router- Source
- ClawHub
- Version observed
- 2.5.4
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-08-28T22:06:30.706Z
- Observations recorded
- 6
- Installs (reported upstream)
- 2
- Weekly downloads (upstream)
- 1,326
- Declared license
- MIT-0
Observation history
2026-09-17T19:21:47.048Z
Fields that differed: license description
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
description |
"Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras plus any OpenAI-compatible endpoint (includi | null |
2026-09-15T17:18:40.381Z
Fields that differed: changelog latestVersion topics
| Field | Before | After |
|---|---|---|
changelog |
"- Bumped version to 2.4.0.1.\n- Minor documentation changes in SKILL.md only; no code or logic changes.\n- Removed the skill-card.md file." | "v2.5.4: model-tags canonicalization — owner-supplied tag set shipped (24 primary: redundant llama-3.3-70b-versatile alias merged into single llama-3.3-70b Groq·Cerebras entry; 8 s |
latestVersion |
"2.4.3" | "2.5.4" |
topics |
["development","free-tier","llm-routing","providers","rate-limits"] | ["free-tier","llm-routing","openai-compatible","providers","rate-limits"] |
2026-09-08T10:18:19.295Z
Fields that differed: changelog latestVersion topics
| Field | Before | After |
|---|---|---|
changelog |
"Category reorganization" | "- Bumped version to 2.4.0.1.\n- Minor documentation changes in SKILL.md only; no code or logic changes.\n- Removed the skill-card.md file." |
latestVersion |
"2.4.2" | "2.4.3" |
topics |
["free-tier","llm-routing","openai-compatible","providers","rate-limits"] | ["development","free-tier","llm-routing","providers","rate-limits"] |
2026-09-07T09:39:20.468Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v2.4.0: --stream live SSE passthrough (same security path, split-chunk buffering, curl exit-code capture, gemini fallback); --learn bounded self-improvement overlay (EWMA latency | "Category reorganization" |
latestVersion |
"2.4.0" | "2.4.2" |
2026-09-06T09:04:43.486Z
Fields that differed: changelog description latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v2.3.0 any-provider-any-agent: pluggable providers.json (any OpenAI-compatible endpoint incl. local Ollama/llama.cpp/vLLM; user routes override builtins), --discover --apply, --js | "v2.4.0: --stream live SSE passthrough (same security path, split-chunk buffering, curl exit-code capture, gemini fallback); --learn bounded self-improvement overlay (EWMA latency |
description |
"Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras. Probes every model on every key, measures r | "Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras plus any OpenAI-compatible endpoint (includi |
latestVersion |
"2.2.9" | "2.4.0" |
summary |
"Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras. Probes every model on every key, measures r | "Quota-aware LLM router that squeezes maximum usable AI out of free-tier API keys across Gemini, Mistral, OpenRouter, Kilo and Cerebras plus any OpenAI-compatible endpoint (includi |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.