🥰 Feature Description
NextChat already overrides the OpenAI host with BASE_URL (README default is https://api.openai.com, without /v1, because NextChat appends /v1). People looking for prepaid, privacy-first inference still have to guess the host, key format, and that adding /v1 themselves produces /v1/v1 and 404s.
Search for pzero returned none. I am not asking for a first-party PZERO provider.
🧐 Proposed Solution
A named PZERO example in the env / custom-endpoint docs.
OPENAI_API_KEY=pzero_YOUR_KEY
BASE_URL=https://api.pzero.studio
Do not set BASE_URL=https://api.pzero.studio/v1. NextChat appends /v1. The chat path is not the base.
In Settings → custom endpoint, same host (https://api.pzero.studio) and a pzero_ key. Model: deepseek-v4-flash (or any live text id from GET https://api.pzero.studio/v1/models, public, no key).
Get a key: https://pzero.studio/agents (sign-in free; min top-up 1 USDC on Base; no starter credits).
Smoke against the host NextChat will call after appending /v1:
curl -sS -X POST "https://api.pzero.studio/v1/chat/completions" \
-H "Authorization: Bearer $PZERO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Hello from PZERO"}],"stream":false}'
If a build does not append /v1 and 404s on https://api.pzero.studio/chat/completions, then that build wants the /v1 root. The README default (https://api.openai.com) is the no-/v1 shape.
I am not asking for a bundled provider. Do not start implementation on my behalf until the board says Ready; the env vars are for users today.
📝 Additional Information
Every AI Credit is at least 20% off $1 list. Usage is paid. Conversion door: https://pzero.studio/agents
🥰 Feature Description
NextChat already overrides the OpenAI host with
BASE_URL(README default ishttps://api.openai.com, without/v1, because NextChat appends/v1). People looking for prepaid, privacy-first inference still have to guess the host, key format, and that adding/v1themselves produces/v1/v1and 404s.Search for
pzeroreturned none. I am not asking for a first-party PZERO provider.🧐 Proposed Solution
A named PZERO example in the env / custom-endpoint docs.
Do not set
BASE_URL=https://api.pzero.studio/v1. NextChat appends/v1. The chat path is not the base.In Settings → custom endpoint, same host (
https://api.pzero.studio) and apzero_key. Model:deepseek-v4-flash(or any live text id fromGET https://api.pzero.studio/v1/models, public, no key).Get a key: https://pzero.studio/agents (sign-in free; min top-up 1 USDC on Base; no starter credits).
Smoke against the host NextChat will call after appending
/v1:If a build does not append
/v1and 404s onhttps://api.pzero.studio/chat/completions, then that build wants the/v1root. The README default (https://api.openai.com) is the no-/v1shape.I am not asking for a bundled provider. Do not start implementation on my behalf until the board says Ready; the env vars are for users today.
📝 Additional Information
Every AI Credit is at least 20% off $1 list. Usage is paid. Conversion door: https://pzero.studio/agents