> AgentRouter
Agent Router is an open-source, public-welfare AI API aggregation platform designed to unify access to agents and MCP tools. It is 'forever free' for both users and developers, providing a discovery registry for skills (ClawHub) and a live A2A directory.
// pros
- Large free credit on signup ($100–$200); community blogs confirm it works for real Claude Code calls
- One key + a single base URL directly reaching multiple upstreams, OpenAI-compatible, simple integration
- Has official docs at docs.agentrouter.org plus multiple positive hands-on reviews/tutorials
- Positioned as a public-welfare site; the free credit is a genuine subsidy, not a paid upsell trap
// cons
- As a resource-limited public-welfare site, it explicitly does not guarantee permanent operation and may shut down anytime
- Operator background is opaque; no disclosed corporate entity
- Aggregation-relay category risk: upstream model authenticity/possible downgrade must be self-verified
- Renewal/rate-limit policy after the free credit is used up is unclear
The signup credit is genuine and integration is simple, making it good for short-term free trials of Claude Code/Codex; but as an unstable public-welfare site, do not rely on it for long-term production or bind critical workloads to it.
community_reputation
Agent Router has multiple positive hands-on reviews (Cnblogs, GitHub Gist, Zhihu) confirming the '$200 signup credit' is real and usable for Claude Code; but community consensus also notes public-welfare sites are unstable (a batch closes roughly every 3 months) and advises short-term use, not long-term production dependence.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
Value taken from the provider’s own published free-tier terms, expressed in USD.
note: Offers $100-$200 free credit bonus for new accounts to bootstrap agent usage.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | $100 free credit on signup ($200 via referral) for aggregated calls to Claude/GPT/DeepSeek etc.; the platform describes itself as public-welfare, resource-limited, and does not guarantee permanent operation. |
| Free tier | free | — | Free | Free | Daily check-in grants on a donation-funded pool; no card and no paid plan observed. |
| Forever Free | free | — | Free | Free | Genuine $0 access for users and developers; optional API key for higher limits. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Claude (full Claude Code family) | — | — | — |
| DeepSeek | — | — | — |
| Zhipu GLM | — | — | — |
| gpt-5 | — | — | 400k |
$ Does AgentRouter have a free tier?
Yes — AgentRouter offers a free tier that we value at roughly $200.00 in free credits. Always confirm current limits on AgentRouter's official pricing page — free tiers change without notice.
$ How much does AgentRouter cost per 1M tokens?
AgentRouter does not publish simple per-1M-token pricing (it may bill per request, per output, or via a subscription plan). Check their official pricing page for exact figures.
$ Is AgentRouter safe to use?
Uprouter rates AgentRouter as medium risk. Highly transparent 'public welfare' mission with open-source roots. However, it relies on community-donated keys or pooled resources, which can lead to stability fluctuations and potential account bans from upstream providers. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
full history →best-effort probes · not a guarantee · last 1d ago
| Checked | Status | Latency |
|---|---|---|
| 1d ago | up | 968ms |
| 3d ago | up | 1171ms |
| 4d ago | up | 1049ms |
| 5d ago | up | 1006ms |
| 7d ago | up | 1314ms |
| 9d ago | up | 1048ms |
| 10d ago | up | 1039ms |
| 12d ago | up | 917ms |
| 13d ago | up | 1055ms |
| 14d ago | up | 953ms |
| 15d ago | up | 979ms |
| 15d ago | up | 1190ms |
| 16d ago | up | 1081ms |
| 17d ago | up | 1142ms |
| 18d ago | up | 1022ms |
| 18d ago | up | 1033ms |
| 19d ago | up | 1251ms |
| 20d ago | up | 1099ms |
| 21d ago | up | 1021ms |
| 21d ago | up | 1078ms |
| 22d ago | up | 1097ms |
| 23d ago | up | 1161ms |
| 24d ago | up | 1199ms |
| 25d ago | up | 1234ms |
| 26d ago | up | 1229ms |
| 26d ago | up | 1025ms |
| 27d ago | up | 1180ms |
| 28d ago | up | 1066ms |
| 29d ago | up | 1049ms |
| 29d ago | up | 1241ms |
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Highly transparent 'public welfare' mission with open-source roots. However, it relies on community-donated keys or pooled resources, which can lead to stability fluctuations and potential account bans from upstream providers.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# AgentRouter's own API — get a key from their dashboard
curl https://YOUR-PROVIDER-ENDPOINT/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-full-claude-code-family",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.