iFlow × WorkDaddy: LLM Provider Integration (2026)

Use iFlow as the engine behind your WorkDaddy agent team: 14 models available, context windows up to 256K tokens, connected in minutes with your own key.

iFlow is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the China Model Providers group. The catalog currently lists 14 models from iFlow: 4 with explicit reasoning, 1 with vision input, and 14 with tool calling — the capability that matters most for agent work. The largest context window reaches 256K tokens.

At a glance

Models available 14
Reasoning models 4
Vision models 1
Tool-calling models 14
Largest context window 256K tokens
API endpoint https://apis.iflow.cn/v1
API key variable IFLOW_API_KEY
SDK adapter @ai-sdk/openai-compatible
Provider docs platform.iflow.cn ↗

Why run WorkDaddy agents on iFlow in 2026

Tool calling, context size, and cost decide how well a provider drives an agent team. iFlow brings 14 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 256K 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 iFlow’s strongest model and bulk work to its cheapest, inside one team.

Best iFlow models for e-commerce agents (2026)

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

  • Kimi-K2-0905 — Kimi model for long-context chat, coding, and agentic reasoning (256K context)

  • Qwen3-235B-A22B-Thinking — Qwen reasoning model for deliberate problem solving, math, and coding (256K context)

  • Qwen3-Coder-Plus — Qwen coding model for software agents, repository edits, and code reasoning (256K context)

  • Qwen3-235B-A22B-Instruct — Qwen instruction model for multilingual chat, reasoning, and tool use (256K context)

  • DeepSeek-R1 — DeepSeek reasoning model for multi-step analysis, math, coding, and tools (128K context)

  • Qwen3-VL-Plus — Qwen vision-language model for visual reasoning, documents, and agent tasks (256K context)

How to connect iFlow to WorkDaddy

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

Featured models

Model Context Reasoning Released
Kimi-K2-0905 256K No 2025-09-05
Qwen3-235B-A22B-Thinking 256K Yes 2025-07-01
Qwen3-Coder-Plus 256K No 2025-07-01
Qwen3-235B-A22B-Instruct 256K No 2025-07-01
DeepSeek-R1 128K Yes 2025-01-20
Qwen3-VL-Plus 256K No 2025-01-01

How it works

01

Connect

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

02

Put agents to work

Pick Kimi-K2-0905 or any of the 14 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 iFlow in 2026?

Yes — iFlow is a supported LLM provider with 14 models in the WorkDaddy catalog, connected with your own API key via the @ai-sdk/openai-compatible adapter.

How many iFlow models can I use with WorkDaddy?

14 models are listed for iFlow, including 4 reasoning models and 1 vision-capable models. The flagship lineup above shows the newest.

What context window do iFlow models offer?

Up to 256K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.

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

It depends on the task mix — iFlow 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.