Home / Inference
BeaverNet
net.beaverai.org/v1Inference gateway, community GPU pool, anonymous tierinference/beavernetJSONcomparereport an errorprovider JSON
- Free allowance
- Works without a key, with limits; a free key gives more.
- Verdict
- caveatusable, with a named limit or an unprobed read path
- Cost
- free tier
- Identity
- anonymousno card, no phone
- Binding limit
- request-rateunpublished: the page says works without a key, with limits, and gives no number; GET /v1/models returns no rate-limit header
- Evidence
- documented4 sources; a first-party page was read and the sentence quoted
- Freshness
- stale on 2026-11-29checked 2026-10-29 (live); stale on 2026-11-29
| Free tier | Works without a key, with limits; a free key gives more. 4 models available; the listing carries a per-model allow_anonymous flag unit requests; metered on request-count; the limits are not stated as numbers on the page; models are served by volunteers sharing their own GPUs |
|---|
| Price | none stated |
|---|
| Limits | - request-rate (binding) unpublished: the page says works without a key, with limits, and gives no number; GET /v1/models returns no rate-limit header source
|
|---|
| Binding | request-rate the unpublished anonymous limit is the stated gate, and only some models allow anonymous calls |
|---|
| Identity | anonymous the page says try it without an account, or sign up with just a name; a GET to /v1/usage, /v1/limits and /v1/chat/completions with no Authorization header answered 401 Missing or invalid Authorization header, so the anonymous route may need a header or token that the page does not show |
|---|
| Egress | not published |
|---|
| Interface | rest |
|---|
| Tooling | any OpenAI-compatible client with base URL https://net.beaverai.org/v1 |
|---|
| Composes with | pairs with prototypes that tolerate a changing set of volunteer-served models; the anonymous tier covers only models flagged allow_anonymous |
|---|
| Reliability | the model set is small and changes with volunteer availability: the home page counts 4 models available |
|---|
| Notes | whether a keyless POST to /v1/chat/completions answers is unverified |
|---|
| Evidence note | documented the claim is first-party and the listing was read by GET; the 401 on keyless GETs to the chat and usage routes conflicts with it, and no completion was sent because probe issues GET and HEAD only |
|---|
Evidence 4
| date | source | what it proved |
|---|
| 2026-10-28 | net.beaverai.org/ | the page states the API works without a key, with limits |
| 2026-10-28 | net.beaverai.org/ | an account is optional and a signup needs just a name |
| 2026-10-28 | net.beaverai.org/ | the home page lists the count of models available |
| 2026-10-28 | net.beaverai.org/v1/models | a keyless GET /v1/models answered 200 and listed bgg1996/melirrhoe, whose allow_anonymous flag follows in the body |
Unknown values 3
$.egress.metered egress metering was not published$.per_object_cap.stated the field does not apply to this kind of offer$.retention.stated the field does not apply to this kind of offer