> ChatAnywhere
ChatAnywhere is a widely used free LLM relay. Users bind a GitHub account to get a free API key and access GPT-4o, Claude, and Gemini models through an OpenAI-compatible interface, optimized for access from mainland China.
// pros
- Real OpenAI-compatible /v1 API with a generatable free key for programmatic calls
- Open-source GitHub project chatanywhere/GPT_API_free, long maintained, high star count, well known in the community
- Direct low-latency access from mainland China, no VPN needed
- Aggregates multiple mainstream LLMs: GPT/DeepSeek/Claude/Gemini/Grok
- Provides status.chatanywhere.tech status page to self-check availability
// cons
- Strict free-tier limits; high-value models (GPT-5/4o) only 5 calls/day, unfit for heavy or production use
- As a third-party relay, the source and compliance of upstream keys cannot be fully verified
- Free key explicitly prohibits commercial use; violation risk is on the user
- Availability depends on the operator; the free tier may be tightened or changed at any time
Good for personal learning, testing, and low-frequency free trials of multiple LLMs; do not rely on the free tier for stable or commercial workloads. Check the GitHub README and status page for current quota and availability, follow its non-commercial terms, and avoid sending sensitive data.
community_reputation
Highly recognized in the Chinese developer community; the GitHub repo has a large star count and many forks/mirrors. Sites like ScamAdviser rate it as basically legitimate. GitHub issues occasionally report 403/errors on the free API, tied to rate limits or transient fluctuations, with no evidence of large-scale exit-scam or key theft. Overall reputation is positive, but it remains a third-party relay with no official guarantee of stability or upstream compliance.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
How we estimated this: the free allowance is converted to a dollar value using the provider’s own pay-as-you-go rates for the models a typical developer would reach for. When the allowance is metered in requests, tokens or minutes rather than dollars, we assume median usage of the cheapest capable model. Because assumptions are involved, the figure carries the est. flag — treat it as an order of magnitude, not a quote.
note: GitHub-bound free key: 10,000 points/day with per-model caps (GPT-5/4o/4.1 5/day, DeepSeek 30/day, mini models 100/day, ~200 req/day total) ≈ $2/mo; personal non-commercial use only.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Bind GitHub to get a free key; 10,000 points/day with per-model limits: GPT-5/GPT-4o/GPT-4.1 5 calls/day, DeepSeek series 30 calls/day, GPT-4o-mini/GPT-3.5-turbo etc. 100 calls/day; roughly 200 requests/day total per IP&Key. Personal non-commercial use only. |
| Free Daily Tier | free | — | — | — | Daily request limits apply based on GitHub account age/activity. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| claude | — | — | — |
| gemini | — | — | — |
| grok | — | — | — |
| Qwen | — | — | — |
| Kimi | — | — | — |
| minimax | — | — | — |
| gpt-5 | — | — | 400k |
| GPT-4o | — | — | 128k |
| gpt-4.1 | — | — | 1.0M |
| GPT-4o-mini | — | — | 128k |
| gpt-3.5-turbo | — | — | 4k |
| DeepSeek-R1 | — | — | 64k |
| DeepSeek V3.2 | — | — | 164k |
<a href="https://uprouter.online/s/chatanywhere-tech" target="_blank" rel="noopener"><img src="https://uprouter.online/badge/chatanywhere-tech.svg" alt="ChatAnywhere 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 ChatAnywhere entry — no tracking, no scripts.
$ Does ChatAnywhere have a free tier?
Yes — ChatAnywhere offers a free tier that we value at roughly $2.00 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on ChatAnywhere's official pricing page — free tiers change without notice.
$ How much does ChatAnywhere cost per 1M tokens?
ChatAnywhere 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 ChatAnywhere safe to use?
Uprouter rates ChatAnywhere as medium risk. Rated medium risk. a free relay that forwards to an upstream with only partial transparency: some model coverage or pricing is confirmed, while other figures rest on third-party reports or a login-gated console. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
$ Can I use ChatAnywhere through Uprouter Connect?
Yes — ChatAnywhere is Connect-compatible. Add your ChatAnywhere 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 13h ago
| Checked | Status | Latency |
|---|---|---|
| 13h ago | up | 349ms |
| 14h ago | up | 869ms |
| 1d ago | up | 357ms |
| 2d ago | up | 307ms |
| 3d ago | up | 304ms |
| 4d ago | up | 909ms |
| 12d ago | up | 525ms |
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 medium risk. a free relay that forwards to an upstream with only partial transparency: some model coverage or pricing is confirmed, while other figures rest on third-party reports or a login-gated console.
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": "claude",
"messages": [{ "role": "user", "content": "Hello via ChatAnywhere" }]
}'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.