Which provider type do I pick in Dify?

Choose "OpenAI-API-compatible" in the model-provider list. Add one entry per model you want to expose, using the exact model ID from /models — each becomes selectable in your Dify apps.

Which models can Dify use through the gateway?

Any chat-capable model in the catalog — GPT, Claude, Gemini, DeepSeek, and Mistral families. The /models page is the source of truth for model IDs and per-token rates.

Does this work from Mainland China?

Yes. The gateway is reachable from Mainland China without a VPN, and the configuration is identical to the global setup.

How do I debug a 401/403/429?

Open Dashboard → Logs first to see whether requests reached the gateway and with what status, then walk the error-codes reference to check env vars, key status, and limits.

Give every Dify app one model provider

Dify is one of the most widely used platforms for building LLM apps and agent workflows. Each app you ship needs a model provider behind it — and juggling one vendor account per family means separate keys, bills, and failure modes. Registering Router One once as an OpenAI-API-compatible provider puts the whole catalog behind a single credential, with every app call traced for cost.

Get your API key

Configuration

In Dify, open Settings → Model Provider → add an OpenAI-API-compatible model, then fill in the model ID, base URL, and key:

dify-model-provider

# Dify → Settings → Model Provider → OpenAI-API-compatible
Model Name:    <model-id-from-/models>
API endpoint:  https://api.router.one/v1
API Key:       sk-your-router-one-key

Pick a model

Copy the exact model ID from the /models page — IDs are case-sensitive, and the page lists each model's context window, capabilities, and current per-token rates. Create a dedicated API key per tool with its own maxSpend cap, so one runaway tool can't affect other workloads.

Verify and observe

After your first request, open Dashboard → Logs to see its full trace: model, tokens, cost, latency, and status code. From here every Dify call has a ledger and a trail instead of being a black box.

FAQ

Which provider type do I pick in Dify?: Choose "OpenAI-API-compatible" in the model-provider list. Add one entry per model you want to expose, using the exact model ID from /models — each becomes selectable in your Dify apps.
Which models can Dify use through the gateway?: Any chat-capable model in the catalog — GPT, Claude, Gemini, DeepSeek, and Mistral families. The /models page is the source of truth for model IDs and per-token rates.
Does this work from Mainland China?: Yes. The gateway is reachable from Mainland China without a VPN, and the configuration is identical to the global setup.
How do I debug a 401/403/429?: Open Dashboard → Logs first to see whether requests reached the gateway and with what status, then walk the error-codes reference to check env vars, key status, and limits.

Get your API key