> Tokeness
Tokeness (tokeness.io) is an AI model aggregator providing access to 50+ frontier models via a standard, unified API protocol. It focuses on stability and security, relaying requests without retaining conversation data. It includes a referral program and free routing options.
// pros
- Built on open-source New API, OpenAI-compatible, Base URL n.tokeness.io/v1
- Low prices (Claude Opus ~0.23x official), 350-450ms domestic latency
- Veridrop: median 83/100 over 4 checks, rated 'pass', covering Claude/OpenAI protocols
// cons
- Prepay-then-call with virtually no free allowance (only ~¥0.5 (≈$0.07) on signup)
- Ultra-cheap channels commonly carry industry risks of stolen keys/dilution/scams/runaway
- The relay can see request content; confidential-data leakage risk
- Fundamentally a paid aggregator, not aligned with the 'free API' positioning
As a paid aggregation relay, its value and test data are decent, but it has almost no free allowance and the inherent risks of ultra-cheap channels; if used, keep deposits small and avoid confidential data. Not a key free-API inclusion target.
community_reputation
Neutral-to-positive (on stability/value): hvoy.ai and Veridrop give pass/positive data; but Linux.do warns of industry-wide stolen-key/runaway risks with ultra-cheap relays, advising deposits under ¥200 (≈$29.76) per top-up. A paid commercial aggregator.
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: New users get only ~¥0.5 (≈$0.07) trial credit at signup, after which calls require prepayment (deducted from balance); there is no public, sustained free allowance, so it is a paid aggregator.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | New users get only ~¥0.5 (≈$0.07) trial credit at signup, after which calls require prepayment (deducted from balance); there is no public, sustained free allowance, so it is a paid aggregator. |
| tokeness/free | free | — | — | — | Free routing for lightweight tasks. |
| Claude Opus 4.8 | payg | — | $5.00 | $25.00 | Standard official price relay. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Claude Opus 4.6/4.7 (mostly paid) | — | — | — |
| OpenAI family (mostly paid) | — | — | — |
$ Does Tokeness have a free tier?
Yes — Tokeness offers a free tier that we value at roughly $29.76 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on Tokeness's official pricing page — free tiers change without notice.
$ How much does Tokeness cost per 1M tokens?
Tokeness 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 Tokeness safe to use?
Uprouter rates Tokeness as medium risk. Rated medium risk. a commercial aggregator routing to many upstreams 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.
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 2h ago
| Checked | Status | Latency |
|---|---|---|
| 2h ago | up | 3563ms |
| 2d ago | up | 3199ms |
| 4d ago | up | 3776ms |
| 5d ago | up | 3386ms |
| 6d ago | up | 3044ms |
| 8d ago | up | 2419ms |
| 9d ago | up | 3860ms |
| 11d ago | up | 3230ms |
| 13d ago | up | 2987ms |
| 14d ago | up | 3342ms |
| 15d ago | up | 3725ms |
| 15d ago | up | 3526ms |
| 16d ago | up | 3371ms |
| 17d ago | up | 1904ms |
| 18d ago | up | 3381ms |
| 19d ago | up | 3434ms |
| 19d ago | up | 3773ms |
| 20d ago | up | 3401ms |
| 21d ago | up | 3179ms |
| 22d ago | up | 2914ms |
| 22d ago | up | 3546ms |
| 23d ago | up | 3262ms |
| 24d ago | up | 3595ms |
| 25d ago | up | 3440ms |
| 26d ago | up | 2843ms |
| 26d ago | up | 3164ms |
| 27d ago | up | 3753ms |
| 28d ago | up | 3505ms |
| 29d ago | up | 3064ms |
| Sep 26, 2026 | up | 2504ms |
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 commercial aggregator routing to many upstreams 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
# Tokeness'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": "mostly-paid-claude-opus-4-6-4-7",
"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.