> JuziAI
Juzi AI (api.juziai.cc) is a Chinese commercial-aggregator relay built on the New-API framework. It aggregates high-end models like GPT-5 and Claude Opus by leveraging various upstream account pools, offering pay-as-you-go access to users in mainland China.
// pros
- New-API based, OpenAI-compatible, has /v1/* and a key-generating console
- Open registration and top-up, with a tiny daily check-in bonus
- Aggregates 117 models covering mainstream LLMs
// cons
- Essentially a pay-per-use relay with negligible free quota (5-20 check-in units)
- Group names like [Kiro]/[ant]/[CC]/[enterprise-cli] suggest abuse of upstream free/subscription tiers; compliance and stability doubtful
- Blank community reputation, no independent review, cannot cross-verify
- Frequent festival discounts and per-call billing obscure true cost
A paid pay-as-you-go relay with negligible free quota and suspected upstream-account abuse; high compliance and stability risk. Not recommended to rely on; if trialing, avoid large deposits.
community_reputation
No independent review or complaint about api.juziai.cc was found; reputation is blank. Probes show many groups likely derived from abusing Kiro/Antigravity/Claude Code/enterprise CLI, a high-risk pattern.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
Free tier present — value not quantified
This provider offers a free tier, but its terms don’t convert cleanly into a USD figure (e.g. request-count limits or capacity-dependent pools). We refuse to print a misleading zero here. See the note below and the official pricing page for the exact limits.
note: Free quota negligible: daily check-in after 10 calls grants 5–20 quota (quota_per_unit=500000 ≈ $1 per 500K quota) → well under $0.01/day; most model_ratio=0 models are pay-per-call. Not quantifiable.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Very small free quota: daily check-in triggered after 10 calls grants 5-20 quota each (quota_per_unit=500000, tiny in real terms); model_ratio=0 models in /api/pricing are mostly quota_type=1 pay-per-call, not free. |
| Free Credits | free | — | — | — | Small signup credit for testing. |
Pricing normalized from public sources — always verify with the provider.
// model prices
<a href="https://uprouter.online/s/api-juziai-cc" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/api-juziai-cc.svg" alt="JuziAI live status on UPROUTER.ONLINE" height="40"></a>Paste this into your README, docs or status page. The badge shows the same best-effort probe data as the directory, refreshes automatically, and links back to the full JuziAI entry — no tracking, no scripts.
$ Does JuziAI have a free tier?
Yes — JuziAI offers a free tier. Always confirm current limits on JuziAI's official pricing page — free tiers change without notice.
$ How much does JuziAI cost per 1M tokens?
JuziAI 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 JuziAI safe to use?
Uprouter rates JuziAI as high risk. Rated high risk. Limited or no official documentation, an opaque or anonymous operator, unstable availability, or pricing and terms that could not be independently confirmed. Relays of this kind may resell shared upstream credits or forward prompts through intermediate hops, so data-handling guarantees are weak. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
$ Can I use JuziAI through Uprouter Connect?
Yes — JuziAI is Connect-compatible. Add your JuziAI API key in Uprouter Connect (encrypted at rest) and route requests to it through one OpenAI- and Claude-compatible API, optionally behind failover aliases. Uprouter meters the traffic in compute at the provider's listed rate.
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 14h ago
| Checked | Status | Latency |
|---|---|---|
| 14h ago | up | 874ms |
| 1d ago | up | 868ms |
| 2d ago | up | 851ms |
| 2d ago | up | 868ms |
| 4d ago | up | 835ms |
| 12d ago | up | 133ms |
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
Rated high risk. Limited or no official documentation, an opaque or anonymous operator, unstable availability, or pricing and terms that could not be independently confirmed. Relays of this kind may resell shared upstream credits or forward prompts through intermediate hops, so data-handling guarantees are weak.
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
curl https://uprouter.online/api/connect/v1/chat/completions \ -H "Authorization: Bearer upr_live_YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{
"model": "a-claude-sonnet-4-6-thinking",
"messages": [{ "role": "user", "content": "Hello via JuziAI" }]
}'Metered in Uprouter compute — the usage log shows which upstream served each request and its exact cost.
Ranked by neutral similarity signals only — live status, Connect compatibility, free-tier shape and free-credit proximity. Commercial relationships never influence this list.