One key instead of many
No signing up with five providers and juggling five keys. One AMP account covers the models your notes need.
Hosted gateway · OpenAI-compatible
Every model,
one endpoint
Subquill AMP is our hosted OpenAI-compatible gateway. Top up once, paste the base URL into Subquill's onboarding, and generate — Claude, GPT, Gemini, DeepSeek, Qwen and more through a single key. No provider roulette, no region blocks.
Pay as you go · No subscription · Cancel any time
Why AMP
What problem is AMP solving?
Works out of the box
AMP speaks the OpenAI chat format Subquill already understands — paste the base URL and key, run the connection test, done.
Transparent billing
A prepaid balance spent per request at provider rates. Watch usage in the console in real time; top up or stop whenever you like.
How it works
Three steps from zero to notes
- 01
Create an account
Sign up in the AMP console and add a pay-as-you-go balance.
- 02
Point Subquill at AMP
In onboarding or Settings, enter the AMP base URL and your API key, then run the one-click connection test.
- 03
Generate notes
Everything else works exactly as before — Subquill just sends your transcripts to the model you picked.
Models
The models your notes need
AMP fronts the major model families through one endpoint. Pick the model name in Subquill and go.
Claude
Strong long-context summarization and structured writing
GPT
Balanced quality and speed for everyday notes
Gemini
Large context windows for long lectures
DeepSeek
Cost-effective open models for bulk jobs
Qwen
Excellent Chinese-language output for Bilibili content
GLM
Bilingual notes with fast streaming responses
This list is indicative — the full model lineup and live prices live in the AMP console.
Pricing
Pay per token. Nothing else.
Prepaid balance, per-token rates — no subscription, no minimum. The rates below are indicative; the console always shows live pricing for every model.
| Model | Input · $/1M | Output · $/1M | Context |
|---|---|---|---|
| Claude Sonnet | $3 | $15 | 200K |
| GPT | $1.25 | $10 | 400K |
| Gemini Flash | $0.30 | $2.50 | 1M |
| DeepSeek V3 | $0.28 | $0.42 | 128K |
| Qwen3 Max | $1.20 | $6 | 256K |
| GLM | $0.60 | $2.20 | 200K |
One base URL, any model
Paste this into Subquill's onboarding (or Settings) as the base URL, create an API key in the console, and pick any model AMP offers.
Privacy
Your transcripts go to the model, nowhere else
AMP is a pass-through gateway: requests are forwarded to the model provider you picked and answers are streamed straight back.
- Zero retention — prompts and responses are not stored
- Nothing is used for model training
- Usage is logged only to meter your balance
- The Subquill app itself still talks to no backend of its own
FAQ
AMP questions, answered.
Amp up your next video
Create an AMP account, top up a few dollars, and turn tonight's lecture into a note you keep.
Get an AMP key