Browser extension · configuration guide + live pricing · sign up for trial credit
Immersive Translate supports custom OpenAI-compatible endpoints. Translation is high-frequency and low-cost per call — cheap fast models are the best fit.
Immersive Translate in one line: Custom OpenAI endpoint with cheap fast models for everyday reading. Recommended models and their market floor prices are in the table below; the full catalog is at https://321ai.cc/en/models/.
| Setting | Value | Notes |
|---|---|---|
Translation service | OpenAI | choose OpenAI or a custom entry in settings |
API address | https://321ai.cc/v1 | |
API Key | API key from the console | |
Model | e.g. gemini-3.5-flash-lite / qwen3.8-flash | pick a cheap, fast model |
1. Extension settings → Translation Service → add OpenAI
2. Enter the API address, key and model name
3. Save, then test on any English page
| What | Where | Notes |
|---|---|---|
| Live market floor pricing | https://321ai.cc/en/models/ | input per 1M tokens, per-supplier quotes on the marketplace |
Prices are the multi-supplier market floor and move in realtime; see all model prices →
Estimate from the live market floor: cheap flash-class models run about $0.001–0.02 per 1M tokens, so everyday reading costs very little — actual usage is billed as consumed.