Scaleway × WorkDaddy: LLM Provider Integration (2026)
Use Scaleway as the engine behind your WorkDaddy agent team: 14 models available, context windows up to 260K tokens, connected in minutes with your own key.
Scaleway is one of 178 LLM providers supported by WorkDaddy’s model layer in 2026, in the Inference Clouds group. The catalog currently lists 14 models from Scaleway: 7 with explicit reasoning, 6 with vision input, and 11 with tool calling — the capability that matters most for agent work. The largest context window reaches 260K tokens.
At a glance
| Models available | 14 |
|---|---|
| Reasoning models | 7 |
| Vision models | 6 |
| Tool-calling models | 11 |
| Largest context window | 260K tokens |
| API endpoint | https://api.scaleway.ai/v1 |
| API key variable | SCALEWAY_API_KEY |
| SDK adapter | @ai-sdk/openai-compatible |
| Provider docs | scaleway.com ↗ |
Why run WorkDaddy agents on Scaleway in 2026
Tool calling, context size, and cost decide how well a provider drives an agent team. Scaleway brings 11 tool-calling models to WorkDaddy — enough to power the full loop of storefront edits, analytics queries, and content production — with 260K 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 Scaleway’s strongest model and bulk work to its cheapest, inside one team.
Best Scaleway models for e-commerce agents (2026)
The current flagships from Scaleway in the WorkDaddy catalog, newest first:
GLM-5.2 — Open flagship GLM for long-horizon coding agents and million-token context work (256K context)
Qwen3.6 35B A3B — Open multimodal Qwen MoE for local agents that need vision, audio, and code (128K context)
Mistral Medium 3.5 128B — Balanced Mistral model for enterprise assistants, multilingual work, and tools (256K context)
Gemma 4 26B A4B IT — Open Gemma instruction model for efficient chat and self-hosted deployments (256K context)
Qwen3.5 397B A17B — Large open Qwen multimodal MoE for visual agents and long technical tasks (256K context)
Qwen3 235B A22B Instruct 2507 — Large open Qwen MoE for multilingual reasoning, coding, and tool use (260K context)
How to connect Scaleway to WorkDaddy
WorkDaddy talks to Scaleway at api.scaleway.ai via the @ai-sdk/openai-compatible adapter. Add your credential (typically SCALEWAY_API_KEY) in Settings → Models, pick a default model, and every agent can use it immediately — or add Scaleway as one engine among several and let tasks route to the best fit.
Featured models
| Model | Context | Reasoning | Released |
|---|---|---|---|
| GLM-5.2 | 256K | Yes | 2026-06-13 |
| Qwen3.6 35B A3B | 128K | Yes | 2026-05-01 |
| Mistral Medium 3.5 128B | 256K | Yes | 2026-04-29 |
| Gemma 4 26B A4B IT | 256K | Yes | 2026-04-01 |
| Qwen3.5 397B A17B | 256K | Yes | 2026-03-17 |
| Qwen3 235B A22B Instruct 2507 | 260K | Yes | 2025-07-01 |
How it works
Connect
In WorkDaddy, open Settings → Models, choose Scaleway, and paste your API key (SCALEWAY_API_KEY). No key? Start on the managed gateway instead.
Put agents to work
Pick GLM-5.2 or any of the 14 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 Scaleway in 2026?
Yes — Scaleway 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 Scaleway models can I use with WorkDaddy?
14 models are listed for Scaleway, including 7 reasoning models and 6 vision-capable models. The flagship lineup above shows the newest.
What context window do Scaleway models offer?
Up to 260K tokens on the largest model — relevant for whole-repo storefront work and long analytics reports.
Is Scaleway the best LLM provider for e-commerce agents?
It depends on the task mix — Scaleway sits in the Inference Clouds 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
NovitaAI
Inference Clouds
Nvidia
Inference Clouds
Venice AI
Inference Clouds
DigitalOcean
Inference Clouds
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.