QiHang × WorkDaddy: LLM Provider Integration (2026)

Use QiHang as the engine behind your WorkDaddy agent team: 9 models available, context windows up to 1M tokens, connected in minutes with your own key.

QiHang is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the China Model Providers group. The catalog currently lists 9 models from QiHang: 9 with explicit reasoning, 9 with vision input, and 9 with tool calling — the capability that matters most for agent work. The largest context window reaches 1M tokens.

At a glance

Models available 9
Reasoning models 9
Vision models 9
Tool-calling models 9
Largest context window 1M tokens
API endpoint https://api.qhaigc.net/v1
API key variable QIHANG_API_KEY
SDK adapter @ai-sdk/openai-compatible
Provider docs qhaigc.net ↗

Why run WorkDaddy agents on QiHang in 2026

Tool calling, context size, and cost decide how well a provider drives an agent team. QiHang brings 9 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 1M 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 QiHang’s strongest model and bulk work to its cheapest, inside one team.

Best QiHang models for e-commerce agents (2026)

The current flagships from QiHang in the WorkDaddy catalog, newest first:

  • Gemini 2.5 Flash — Fast Gemini model balancing multimodal reasoning, tool use, and cost (1M context)

  • Gemini 3 Flash Preview — Fast Gemini model balancing multimodal reasoning, tool use, and cost (1M context)

  • GPT-5.2 Codex — Coding-optimized GPT model for repository edits, reviews, and agentic software work (400K context)

  • GPT-5.2 — GPT model for general reasoning, writing, coding, and tool-assisted tasks (400K context)

  • Gemini 3 Pro Preview — Advanced Gemini model for complex reasoning, coding, and multimodal analysis (1M context)

  • Claude Opus 4.5 — Flagship Claude model for deep reasoning, coding, and long-horizon agents (200K context)

How to connect QiHang to WorkDaddy

WorkDaddy talks to QiHang at api.qhaigc.net via the @ai-sdk/openai-compatible adapter. Add your credential (typically QIHANG_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add QiHang as one engine among several and let tasks route to the best fit.

Featured models

Model Context Reasoning Released
Gemini 2.5 Flash 1M Yes 2025-12-17
Gemini 3 Flash Preview 1M Yes 2025-12-17
GPT-5.2 Codex 400K Yes 2025-12-11
GPT-5.2 400K Yes 2025-12-11
Gemini 3 Pro Preview 1M Yes 2025-11-19
Claude Opus 4.5 200K Yes 2025-11-01

How it works

01

Connect

In WorkDaddy, open Settings → Models, choose QiHang, and paste your API key (QIHANG_API_KEY). No key? Start on the managed gateway instead.

02

Put agents to work

Pick Gemini 2.5 Flash or any of the 9 available models as your default — per-agent overrides let you match model to task.

03

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 QiHang in 2026?

Yes — QiHang is a supported LLM provider with 9 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.

How many QiHang models can I use with WorkDaddy?

9 models are listed for QiHang, including 9 reasoning models and 9 vision-capable models. The flagship lineup above shows the newest.

What context window do QiHang models offer?

Up to 1M tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.

Is QiHang the best LLM provider for e-commerce agents?

It depends on the task mix — QiHang 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.

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.