Plugins

Painel de uso na barra lateral que atribui tokens ao site de retransmissão que atendeu cada solicitação, lido a partir da sua configuração de provedor existente: totais de hoje/mês/todo o período, detalhamentos por site e por modelo, um mapa de calor de atividade anual e saldos de New API / Sub2API / DeepSeek.

Provedor LLM NewAPI (gateway compatível com OpenAI): registra uma rota `newapi` com descoberta de modelos somente para chat, preenche automaticamente os parâmetros do modelo (janela de contexto, esforço de raciocínio) a partir do models.dev, e adiciona uma seção de configurações web para a URL base e a chave de API.

Session-affinity routing for LLM gateways: injects the session ID into every request sent to NewApi-style gateways so the gateway can pin requests per session and raise prompt-cache hits; takes over the official pi-ai routing on install and restores it on uninstall.

Multi-platform LLM balance and quota panel: configure DeepSeek, OpenRouter, Kimi, Zhipu GLM, MiniMax, NewApi or custom endpoints, poll on a schedule, draw balance and quota trend charts, and push threshold and window-reset notices through multiple channels.

Call a new-api (one-api style) relay station's video model from the conversation with @-referenced image/video materials, supporting Seedance 2.0 and Happyhorse text-to-video and image-to-video across four relay protocols.

DSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models

New API OAuth provider, account configuration, model discovery, and model adapter for DeepSeek Harness

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model