diff --git a/docs/customize/model-providers/top-level/openai.mdx b/docs/customize/model-providers/top-level/openai.mdx index 4d7326b479e..8619cd116fc 100644 --- a/docs/customize/model-providers/top-level/openai.mdx +++ b/docs/customize/model-providers/top-level/openai.mdx @@ -96,6 +96,46 @@ If you are using an OpenAI API compatible providers, you can change the `apiBase +### PZERO + +[PZERO](https://pzero.studio/agents) is a prepaid OpenAI-compatible inference service. It uses a `pzero_` API key and serves `deepseek-v4-flash` among other models. + + + + ```yaml title="config.yaml" + name: PZERO + version: 0.0.1 + schema: v1 + + models: + - name: PZERO + provider: openai + model: deepseek-v4-flash + apiBase: https://api.pzero.studio/v1 + apiKey: pzero_YOUR_KEY + useResponsesApi: false + ``` + + + ```json title="config.json" + { + "models": [ + { + "title": "PZERO", + "provider": "openai", + "model": "deepseek-v4-flash", + "apiBase": "https://api.pzero.studio/v1", + "apiKey": "pzero_YOUR_KEY", + "useResponsesApi": false + } + ] + } + ``` + + + +[Get a PZERO API key](https://pzero.studio/agents) (sign-in free; min top-up 1 USDC on Base; no starter credits). The public model catalog is available without a key: `GET https://api.pzero.studio/v1/models`. + ### How to Force Legacy Completions Endpoint Usage To force usage of `completions` instead of `chat/completions` endpoint you can set: