Home / Inference
DG AI API (dg-ai.scriptsnsenses.workers.dev)
dg-ai.scriptsnsenses.workers.dev/v1Inference gateway, keyless free public betainference/dg-ai-apiJSONcomparereport an errorprovider JSON
- Free allowance
- Free public beta with no key required: 18 models live, auth is optional and a placeholder of dashes is accepted; the anonymous tier is 8 requests per 10 s
- Verdict
- caveatusable, with a named limit or an unprobed read path
- Cost
- free tier
- Identity
- anonymous?placeholder, not evidence; card unknown, phone unknown
- Binding limit
- request-rateanonymous tier 8 requests per 10 s; a verified tier is 16 per 10 s (stated as "anon 8/10s · verified 16/10s")
- Evidence
- documented5 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 | Free public beta with no key required: 18 models live, auth is optional and a placeholder of dashes is accepted; the anonymous tier is 8 requests per 10 s unit requests; metered on request-count; GET /v1/models lists 18 ids; the page labels three backends (Cloudflare Workers AI, freeAI gateways, SurfSense) plus NVIDIA NIM, and which model actually serves an id with another vendor's name is not observed |
|---|
| Price | none stated |
|---|
| Limits | - request-rate (binding) anonymous tier 8 requests per 10 s; a verified tier is 16 per 10 s (stated as "anon 8/10s · verified 16/10s") source
|
|---|
| Binding | request-rate the anonymous tier ceiling of 8 per 10 s binds; what verification requires was not read |
|---|
| Identity | anonymous (placeholder) none for the anonymous tier: auth is optional, and a placeholder or no header is accepted as anonymous. A verified tier raises the quota; what verifying needs was not read: unverified |
|---|
| Egress | not published |
|---|
| Interface | rest |
|---|
| Tooling | POST /v1/chat with {"model": id, "messages": [...]}; the chat route is /v1/chat, not /v1/chat/completions, which answers "Route not found" to a GET. A placeholder Authorization or X-API-Key of dashes, or no header, is accepted |
|---|
| Composes with | pairs with prototypes that need a free OpenAI-shaped call; image and voice routes exist beside chat |
|---|
| Reliability | the page claims 98.7% uptime over 90 days; no x-ratelimit header is returned on GET /v1/models, only CORS headers |
|---|
| Notes | ids such as claude-sonnet-3.5 and gemini-2.5-pro are labelled by their upstream vendor in the listing and are served through the freeAI gateway backend named on the page; the served model is unverified |
|---|
| Evidence note | documented the model list was read by a keyless GET; no completion was sent because probe issues GET and HEAD only, so the echoed model and the answer are unverified |
|---|
| Parsed numbers | |
|---|
Evidence 5
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