ModelScope × WorkDaddy: LLM Provider Integration (2026)
Use ModelScope as the engine behind your WorkDaddy agent team: 7 models available, context windows up to 262K tokens, connected in minutes with your own key.
ModelScope is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the China Model Providers group. The catalog currently lists 7 models from ModelScope: 4 with explicit reasoning, 0 with vision input, and 7 with tool calling — the capability that matters most for agent work. The largest context window reaches 262K tokens.
At a glance
| Models available | 7 |
|---|---|
| Reasoning models | 4 |
| Vision models | 0 |
| Tool-calling models | 7 |
| Largest context window | 262K tokens |
| API endpoint | https://api-inference.modelscope.cn/v1 |
| API key variable | MODELSCOPE_API_KEY |
| SDK adapter | @ai-sdk/openai-compatible |
| Provider docs | modelscope.cn ↗ |
Why run WorkDaddy agents on ModelScope in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. ModelScope brings 7 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 262K 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 ModelScope’s strongest model and bulk work to its cheapest, inside one team.
Best ModelScope models for e-commerce agents (2026)
The current flagships from ModelScope in the WorkDaddy catalog, newest first:
GLM-4.6 — Flagship GLM model for hybrid reasoning, coding, and agentic engineering (203K context)
Qwen3 Coder 30B A3B Instruct — Qwen coding model for software agents, repository edits, and code reasoning (262K context)
Qwen3 30B A3B Thinking 2507 — Qwen reasoning model for deliberate problem solving, math, and coding (262K context)
Qwen3 30B A3B Instruct 2507 — Qwen instruction model for multilingual chat, reasoning, and tool use (262K context)
GLM-4.5 — Flagship GLM model for hybrid reasoning, coding, and agentic engineering (131K context)
Qwen3-235B-A22B-Thinking-2507 — Qwen reasoning model for deliberate problem solving, math, and coding (262K context)
How to connect ModelScope to WorkDaddy
WorkDaddy talks to ModelScope at api-inference.modelscope.cn via the @ai-sdk/openai-compatible adapter. Add your credential (typically MODELSCOPE_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add ModelScope as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| GLM-4.6 | 203K | Yes | 2025-09-30 |
| Qwen3 Coder 30B A3B Instruct | 262K | No | 2025-07-31 |
| Qwen3 30B A3B Thinking 2507 | 262K | Yes | 2025-07-30 |
| Qwen3 30B A3B Instruct 2507 | 262K | No | 2025-07-30 |
| GLM-4.5 | 131K | Yes | 2025-07-28 |
| Qwen3-235B-A22B-Thinking-2507 | 262K | Yes | 2025-07-25 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose ModelScope, and paste your API key (MODELSCOPE_API_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick GLM-4.6 or any of the 7 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 ModelScope in 2026?
Yes — ModelScope is a supported LLM provider with 7 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.
How many ModelScope models can I use with WorkDaddy?
7 models are listed for ModelScope, including 4 reasoning models and 0 vision-capable models. The flagship lineup above shows the newest.
What context window do ModelScope models offer?
Up to 262K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is ModelScope the best LLM provider for e-commerce agents?
It depends on the task mix — ModelScope 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.