AI Gateway Jev returns 403 no_providers_available on Hobby team

AI Gateway Jev returns 403 no_providers_available on Hobby team - Help - Vercel Community

Hi,

I'm seeing a reproducible issue with Vercel AI Gateway when using:

model: typesafe-ai/jev endpoint: POST /v1/evaluate

The request returns:

HTTP 403 error type: no_providers_available

I confirmed the following:

GET /v1/models returns 200
typesafe-ai/jev is present in the model catalog
AI_GATEWAY_API_KEY authentication works
Card verification is complete
AI Gateway budget is configured
Provider Allowlist is disabled
Zero Data Retention is disabled
No custom routing rule is configured
The same native /v1/evaluate endpoint previously returned HTTP 200
Other application/database state is unchanged

I also tried pinning the provider explicitly:

providerOptions.gateway.only = ["typesafe-ai"]

This still returned HTTP 403 / no_providers_available.

Request ID:

kix1::cle1::g8xr7-1790658426354-04115e817031

The AI Gateway log shows:

Provider: TypeSafe AI Model: Jev

An earlier failed request was routed to DigitalOcean, but pinning TypeSafe AI directly also fails, so this does not appear to be specific to the DigitalOcean route.

Could you please check whether there is a provisioning, entitlement, or provider-availability issue for typesafe-ai/jev on this Hobby team?

I can provide additional request IDs if needed, but I will not post API keys or Authorization headers.

Thank you.

I am seeing the same error on my Ortus Lab Hobby team as of 4 October 2026.

A single connection-only request to POST /v1/evaluate, using typesafe-ai/jev with providerOptions.gateway.only = ["typesafe-ai"], returned HTTP 403 / no_providers_available. No retries were made.

Gateway generation: gen_01M42Z5VSGVE2NZHP2PFH7B9JS Request ID: kix1::cle1::xxhnt-1791101169365-b47ac4afa936 Timestamp: 2026-10-04 08:06:09.456 UTC

The authenticated dashboard shows provider allowlist, model allowlist and ZDR disabled. The request log shows TypeSafe AI / Jev and no reported usage. Provider reachability and the root cause are still unknown.

Could Vercel confirm whether this team is currently eligible to access Jev and identify why this generation had no available provider? No API keys or Authorization headers are included.

Hi Vercel team,

I'm experiencing the same issue with typesafe-ai/jev-1.14.0 on my Hobby team.

POST /v1/evaluate returns HTTP 403.
The AI Gateway key is recognised.
The model page says the TypeSafe AI provider is unavailable to my team.
Zero Data Retention is disabled.
The request reaches TypeSafe AI but reports no token usage.
AI Gateway Logs confirm $0 charged.
Observed on 3 November 2026.

Could you confirm whether this is a provider availability, account entitlement or provisioning issue, and whether access can be restored on Hobby?

I can provide the Gateway request ID privately if needed.

Thank you!

Vercel Staff

Hi everyone, as per our pricing page (https://vercel.com/ai-gateway/models/jev), you cannot use free credits for Jev models on either TypeSafe or DigitalOcean providers. Let me know if you have another question.