D.Run (China) × WorkDaddy: LLM Provider Integration (2026)
Use D.Run (China) as the engine behind your WorkDaddy agent team: 3 models available, context windows up to 205K tokens, connected in minutes with your own key.
D.Run (China) is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the China Model Providers group. The catalog currently lists 3 models from D.Run (China): 2 with explicit reasoning, 0 with vision input, and 3 with tool calling — the capability that matters most for agent work. The largest context window reaches 205K tokens.
At a glance
| Models available | 3 |
|---|---|
| Reasoning models | 2 |
| Vision models | 0 |
| Tool-calling models | 3 |
| Largest context window | 205K tokens |
| API endpoint | https://chat.d.run/v1 |
| API key variable | DRUN_API_KEY |
| SDK adapter | @ai-sdk/openai-compatible |
| Provider docs | d.run ↗ |
Why run WorkDaddy agents on D.Run (China) in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. D.Run (China) brings 3 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 205K tokens of context at the top end for whole-codebase and long-report work. Because WorkDaddy is model-agnostic, you can route heavy reasoning to D.Run (China)’s strongest model and bulk work to its cheapest, inside one team.
Best D.Run (China) models for e-commerce agents (2026)
The current flagships from D.Run (China) in the WorkDaddy catalog, newest first:
MiniMax M2.5 — MiniMax model for chat, coding, office work, and agentic tasks (205K context)
DeepSeek R1 — DeepSeek reasoning model for multi-step analysis, math, coding, and tools (131K context)
DeepSeek V3 — DeepSeek chat model for instruction following, coding, and analysis (131K context)
How to connect D.Run (China) to WorkDaddy
WorkDaddy talks to D.Run (China) at chat.d.run via the @ai-sdk/openai-compatible adapter. Add your credential (typically DRUN_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add D.Run (China) as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| MiniMax M2.5 | 205K | Yes | 2025-03-01 |
| DeepSeek R1 | 131K | Yes | 2025-01-20 |
| DeepSeek V3 | 131K | No | 2024-12-26 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose D.Run (China), and paste your API key (DRUN_API_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick MiniMax M2.5 or any of the 3 available models as your default — per-agent overrides let you match model to task.
Review and approve
Agent output stays draft-first regardless of the model: review diffs and approve actions exactly as before.
Frequently asked questions
Does WorkDaddy support D.Run (China) in 2026?
Yes — D.Run (China) is a supported LLM provider with 3 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.
How many D.Run (China) models can I use with WorkDaddy?
3 models are listed for D.Run (China), including 2 reasoning models and 0 vision-capable models. The flagship lineup above shows the newest.
What context window do D.Run (China) models offer?
Up to 205K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is D.Run (China) the best LLM provider for e-commerce agents?
It depends on the task mix — D.Run (China) sits in the China Model Providers group. WorkDaddy is model-agnostic, so the practical answer in 2026 is to combine providers: route each agent task to whichever model fits best.
Keep reading
Qiniu
China Model Providers
Alibaba (China)
China Model Providers
Jiekou.AI
China Model Providers
Alibaba
China Model Providers
Explore more integration directories
Put the team to work on your store
Connect your storefront, analytics, and email stack, set a goal, and let the agents run the work end to end. Start on the free plan with your own model key.