Models & Providers

Official-style model + reasoning-effort control for the composer. Reuses the official picker and always offers Off/Low/High/Max — exactly like the official DeepSeek control — even when a gateway model declares no reasoning effort, with a small hint at the panel bottom when upstream does not natively support it.

Use your ChatGPT subscription in DeepSeek Harness. Sign in, choose GPT, and work with images and built-in tools.

dsh X magpie 简化集成 magpie 供应商的 dsh 插件

Sync one sub2api instance's groups, keys, and models into dsh-llm-pi-ai provider routes: panel-driven login (password / OAuth), one relay key one provider.

模型故障转移队列：P1 限额/限流/不可用时自动切到队列下一个模型继续，全部图形界面配置 | Model fallback queue for DeepSeek Harness: auto-switch to the next model when the current one hits quota or rate limits

Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.

Syncs DSH model providers and models across computers through any WebDAV server: the backup is sealed with a passphrase before it leaves this machine, so a new machine opens with the same model list.

Connects an existing local MiniMax Code sign-in to DeepSeek Harness through a loopback reverse proxy without storing an API key or signing out.

Connects the OpenCode Zen anonymous free lane to DeepSeek Harness: refresh the model list from upstream, tick which models the opencode provider exposes, test any of them with a real request that ends in one of seven verdicts, and order both the settings card and the model selector by a hand-written S/A/B/C capability rating.

Stops compaction summaries and session titles from burning their output budget on reasoning, by lowering the thinking level and raising the token floor for auxiliary calls only.

Connects DSH to the local Qoder desktop client's sign-in to expose Qoder CN models (qmodel, qfmodel). Windows only: the credential is decrypted with DPAPI.

Use your ChatGPT account to bring Codex models into DSH: choose models and thinking effort, chat with images, use tools and skills, approve local tasks, answer interactive questions, continue and compact long conversations, check quota and Token history, and maintain a supported Windows screenshot helper.

Volcengine Ark Coding Plan provider route for DeepSeek Harness with all 15 Coding Plan models and per-model reasoning-effort control, generated from a single source and drift-checked weekly.

Manages a relay station's many groups and rates for DSH, switching the station's billing group in place and refreshing the model list and rate on stations that expose /v1/token/group; stations without it fall back to read-only and keep serving models.

Adds per-member model and reasoning-effort routing to DeepSeek Desktop Agent Teams, plus leader-initiated release of a teammate subagent run instance.

Bridges the third-party providers saved in a local cc-switch app into DeepSeek Harness: Anthropic-format tool groups become adapter routes, Codex groups are handed to the built-in pi-ai adapter, and a settings page picks which groups to import and in which order.

Use ChatGPT subscriptions in DeepSeek Harness Desktop via official Sign in with ChatGPT, with dynamic Agent registration and native model and reasoning selection.

Exposes every model of every provider configured in DeepSeek Harness through one OpenAI-compatible endpoint on a fixed loopback port, with a sidebar page for the base URL, key, port and model ids.

Configure model providers by probing their endpoint, check DeepSeek Harness health, and repair what can be fixed.

One-click add Agnes AI free models to DeepSeek Harness.

Exposes the accounts in a local CC Switch database to DeepSeek Harness: every account (Claude Code, Codex, OpenCode, Grok Build) becomes a model category in the picker, and the SQLite database is re-read on every model listing and request, so switching accounts in CC Switch needs no DSH restart. Requires CC Switch and the DSH desktop app.

Adds Standard Compute as an OpenAI-compatible model provider through the built-in pi-ai adapter, with its standardcompute router model and two direct model pins; configuration only, no code.

Only the domains you list go through a proxy: add a model host that needs the proxy to be reachable, and web search plus every other request stays on the normal network. Multiple named proxies can serve different domains, with a never-proxy list on top; saved settings apply on the next request without a restart.

Tiers free-channel models into three 1M fallback chains plus a custom chain; orders them by measured throughput, drops models below throughput or error-rate thresholds, and rotates accounts. Requires an OpenAI-compatible gateway (default :8326).