Newton’s
Menu
Create account

ENTERPRISE GATEWAYS & PROXY SERVERS

Unify LiteLLM with
Newton’s Edge Gateway.

LiteLLM is the industry-standard router for enterprise AI engineering teams. Pair LiteLLM’s governance, cost budgets, and rate limits with Newton’s edge reliability, global sub-50ms TTFT, and automatic prompt caching.

CLAIM $1 STARTER CREDITLiteLLM vs OpenRouter Deep Dive →All Integrations →

Why Route LiteLLM through Newton’s?

Combine local policy orchestration with global edge execution.

01 · GLOBAL EDGE TOPOLOGY

Sub-50ms Edge Termination

Eliminate geographic latency. Cloudflare Workers terminate your connection at the nearest edge PoP, maintaining warm persistent HTTP/2 and HTTP/3 multiplexing.

02 · POOLED CAPACITY FAILOVER

Bypass Upstream 429 & 503 Errors

When upstream providers experience capacity crunches or rate limits, Newton’s edge proxy automatically fails over across verified model clusters with zero configuration changes.

03 · ONE INVOICE & REAL-TIME LEDGER

No Surprise Billing Overages

Every request settles against an immutable prepaid ledger with cryptographic transaction verification. No $10,000 surprise invoices at the end of the month.

LiteLLM Proxy Configuration

Drop this into your team’s config.yaml file.

config.yaml

model_list:
  - model_name: gpt-5.6-sol
    litellm_params:
      model: openai/gpt-5.6-sol
      api_base: "https://newtons.dev/api/v1"
      api_key: os.environ/NEWTONS_API_KEY
  - model_name: claude-sonnet-5
    litellm_params:
      model: openai/claude-sonnet-5
      api_base: "https://newtons.dev/api/v1"
      api_key: os.environ/NEWTONS_API_KEY
  - model_name: deepseek-reasoner
    litellm_params:
      model: openai/deepseek-reasoner
      api_base: "https://newtons.dev/api/v1"
      api_key: os.environ/NEWTONS_API_KEY

general_settings:
  master_key: sk-your-internal-master-key

Launch Proxy

export NEWTONS_API_KEY="newt_your_api_key"
litellm --config config.yaml --port 4000

Python SDK Direct Usage

import litellm

response = litellm.completion(
    model="openai/gpt-5.6-sol",
    messages=[{"role": "user", "content": "Hello Newton's via LiteLLM!"}],
    api_base="https://newtons.dev/api/v1",
    api_key="newt_your_api_key",
)
print(response.choices[0].message.content)