Put every model behind Immersive Translate's custom API
Immersive Translate is one of the most popular bilingual translation extensions — web pages, PDFs, ebooks, and subtitles, translated inline as you read. Translation is a steady token burn: every page you open spends a little more, so the model's per-token rate matters more here than almost anywhere else. The extension's custom OpenAI-compatible setup takes one endpoint and one key: point it at Router One and pick any chat model in the catalog — pay-as-you-go, as low as 10% of official list prices on select models, with a per-request cost trace that shows what your reading actually costs.
Configure Immersive Translate to use the Router One base URL
In Immersive Translate, open Settings → Translation Services → OpenAI, switch the key type to Custom API Key, then expand the advanced options and fill in the custom endpoint — note it takes the full /chat/completions path, not just the base URL — plus a model ID from the /models page:
# Immersive Translate → Settings → Translation Services → OpenAI # 沉浸式翻译 → 设置 → 翻译服务 → OpenAI API Key type（API Key 类型）: Custom API Key（自定义 API Key） APIKEY: sk-your-router-one-key Custom endpoint（自定义 API 接口地址，须含 /chat/completions）: https://api.router.one/v1/chat/completions Custom model（自定义模型）: <model-id-from-/models>
Which model ID should Immersive Translate send?
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 the Immersive Translate call in your request trace
After your first request, open Dashboard → Logs to see its full trace: model, tokens, cost, latency, and status code. From here every Immersive Translate call has a ledger and a trail instead of being a black box.
FAQ
Why does Immersive Translate reject my base URL?
The custom endpoint field expects the full path including /chat/completions — https://api.router.one/v1/chat/completions — not the bare /v1 base URL most SDKs take. If translations fail immediately, check that suffix first, then verify the model ID matches /models exactly.
Which models can Immersive Translate use through the gateway?
Any chat-capable model in the catalog — GPT, Claude, Gemini, Grok, DeepSeek, GLM, and Kimi 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.