> Agnes AI
Agnes AI, developed by Singapore-based Sapiens AI, is an omni-modal AI platform offering indefinitely free access to core text, image, and video models. It supports OpenAI-compatible API keys and tiered 'Token Plans' for production-level throughput.
// pros
- Provides an OpenAI-compatible free API (base URL apihub.agnes-ai.com/v1, keys created at platform.agnes-ai.com)
- Omni-modal coverage: text + image + video, low integration barrier
- Parent company Sapiens AI has a legitimate background; ScamAdviser gives a high trust score with no fraud reports
- Free tier is adequate for individual developers and prototyping; reasonably fast
// cons
- Very young service (about 3-4 months live); long-term stability and sustainability of the free promise are untested
- Image/video output reported as unstable, needing repeated verification; bugs cause workflow friction
- Suspicious look-alike domains exist (e.g. agnes-ai.top), a brand-fragmentation/phishing risk
- Business model unclear; 'indefinitely free' may change with funding/cost pressures
Usable as a free omni-modal API for personal prototypes and experiments; given the short track record and unverified free promise, avoid production-critical paths and sensitive data, and verify the official main domain to avoid look-alike phishing.
community_reputation
Chinese tech media (QbitAI, 36Kr, PingWest, BAAI hub) and third-party reviews are broadly neutral-to-positive: the product is real and not a scam, and the free API is fine for prototyping; but they consistently caution about its short track record, unstable output, and that 'free does not equal success', with longevity hinging on stability and docs. ScamAdviser rates the main domain highly.
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: Advertised as indefinitely free core-model API with rate/volume caps; signup probe hints ~$1 starter credit (counted). Free tier reportedly sufficient for individual developers and demos.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Officially advertised as 'indefinitely free' core-model API; signup probe hints at roughly a $1 starter credit. The free tier has rate and volume caps; media say it is generally sufficient for individual developers, demos and prototypes. |
| Free / Default | free | — | Free | Free | Indefinite free access to core models; 1 RPM for video, 30 RPM for text. |
| Token Plan Starter | subscription | — | — | — | 1,500 agnes-2.5-flash requests per 5 hours; 4,000 images per day. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Agnes-2.0-Flash (text) | — | — | — |
| Agnes-Image-2.0-Flash (image) | — | — | — |
| Agnes-Video-V2.0 (video) | — | — | — |
$ Does Agnes AI have a free tier?
Yes — Agnes AI offers a free tier that we value at roughly $1.00 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on Agnes AI's official pricing page — free tiers change without notice.
$ How much does Agnes AI cost per 1M tokens?
Agnes AI 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 Agnes AI safe to use?
Uprouter rates Agnes AI as medium risk. Singapore-based lab with a clear roadmap and documentation. While the free tier is generous, the long-term sustainability of 'indefinitely free' video/image models depends on their proprietary hardware efficiency. 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 | 533ms |
| 2d ago | up | 274ms |
| 4d ago | up | 274ms |
| 5d ago | up | 301ms |
| 7d ago | up | 328ms |
| 8d ago | up | 288ms |
| 10d ago | up | 267ms |
| 12d ago | up | 262ms |
| 13d ago | up | 277ms |
| 15d ago | up | 295ms |
| 16d ago | up | 320ms |
| 18d ago | up | 303ms |
| 19d ago | up | 290ms |
| 21d ago | up | 295ms |
| 22d ago | up | 320ms |
| 24d ago | up | 266ms |
| 25d ago | up | 508ms |
| 27d ago | up | 278ms |
| 28d ago | up | 1055ms |
| Oct 13, 2026 | up | 264ms |
| Oct 12, 2026 | up | 292ms |
| Oct 11, 2026 | up | 273ms |
| Oct 10, 2026 | up | 290ms |
| Oct 10, 2026 | up | 1284ms |
| Oct 9, 2026 | up | 289ms |
| Oct 8, 2026 | up | 268ms |
| Oct 7, 2026 | up | 1013ms |
| Oct 7, 2026 | up | 1042ms |
| Oct 6, 2026 | up | 336ms |
| Oct 5, 2026 | up | 292ms |
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
Singapore-based lab with a clear roadmap and documentation. While the free tier is generous, the long-term sustainability of 'indefinitely free' video/image models depends on their proprietary hardware efficiency.
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
# Agnes AI'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": "agnes-2-0-flash-text",
"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.