Sub-50ms Time to First Token
Tab-autocomplete requires immediate responses. Newton’s terminates TLS at 330+ Cloudflare edge PoPs globally, shaving 100ms+ of network latency off every keystroke.
VS CODE & JETBRAINS OPEN SOURCE ASSISTANT
Continue.dev brings open-source AI assistance directly into VS Code, IntelliJ, and PyCharm. Route your completions through Newton’s edge for instant sub-50ms token streaming, automatic prompt caching discounts, and zero monthly subscriptions.
Why Continue users switch from direct provider keys to Newton’s edge proxy.
Tab-autocomplete requires immediate responses. Newton’s terminates TLS at 330+ Cloudflare edge PoPs globally, shaving 100ms+ of network latency off every keystroke.
Continue repeatedly passes your entire open file and codebase context. Newton’s edge automatically snapshots and caches prompts so you stop paying full price on repetitive hits.
One Newton’s API key works everywhere Continue runs—from Visual Studio Code to Android Studio, WebStorm, and PyCharm—with centralized real-time credit tracking.
Add this to your Continue ~/.continue/config.yaml (or config.json).
models:
- name: Newton's GPT-5.6 Sol
provider: openai
model: gpt-5.6-sol
apiKey: "<YOUR_NEWTONS_API_KEY>"
apiBase: "https://newtons.dev/api/v1"
- name: Newton's Claude Sonnet 5
provider: openai
model: claude-sonnet-5
apiKey: "<YOUR_NEWTONS_API_KEY>"
apiBase: "https://newtons.dev/api/v1"
- name: Newton's DeepSeek Reasoner
provider: openai
model: deepseek-reasoner
apiKey: "<YOUR_NEWTONS_API_KEY>"
apiBase: "https://newtons.dev/api/v1"
tabAutocompleteModel:
name: Newton's Fast Autocomplete
provider: openai
model: gpt-5.6-terra
apiKey: "<YOUR_NEWTONS_API_KEY>"
apiBase: "https://newtons.dev/api/v1"{
"models": [
{
"title": "Newton's GPT-5.6 Sol",
"provider": "openai",
"model": "gpt-5.6-sol",
"apiBase": "https://newtons.dev/api/v1",
"apiKey": "<YOUR_NEWTONS_API_KEY>"
}
]
}Open Continue in your IDE sidebar (Cmd+L / Ctrl+L) and start asking questions or generating full repository diffs.