Neural Inverse is Open Source →

Bring Your Own LLM

Neural Inverse connects directly to your LLM provider of choice. No proxy server. No token routing. No data leaving your machine unless you send it to the provider yourself.


20 Providers. One IDE.

Cloud API Providers

ProviderStrengthAuth
AnthropicBest coding models (Claude Opus/Sonnet)API key
OpenAIGPT-5.4, o3, o4-mini reasoningAPI key
Google Gemini1M context, multimodalAPI key
xAIGrok-4, fast reasoningAPI key
DeepSeekLow-cost reasoning (DeepSeek-R1)API key
MistralDevstral coding, Codestral FIMAPI key
GroqUltra-fast open model inferenceAPI key
OpenRouter300+ models, single API keyAPI key
GitHub Models40+ models from one GitHub PATGitHub PAT
Fireworks AIFastest open-model inference, native toolsAPI key
Cerebras2000+ tok/s wafer-scale hardwareAPI key

Infrastructure Providers

ProviderUse CaseAuth
AWS BedrockEnterprise, VPC-internal modelsAWS credentials
Google Vertex AIGCP-hosted GeminiService account
Microsoft AzureAzure-hosted OpenAI modelsResource key

Local / Self-Hosted

ProviderUse Case
OllamaRun models on your laptop (auto-detected)
vLLMProduction-grade local serving
LM StudioDesktop model runner (auto-detected)
LiteLLMUniversal proxy for any backend
OpenAI-CompatibleAny OpenAI-format endpoint

Per-Feature Model Selection

Different tasks need different models. Neural Inverse lets you assign independently:

FeatureBest forRecommended model type
Chat (Ctrl+L)Complex code generation, architecturePowerful (Claude Opus, GPT-5.4, Gemini Pro)
Inline Edit (Ctrl+K)Quick targeted changesMid-tier (Sonnet, GPT-4.1-mini)
Autocomplete (Tab)Real-time suggestionsFast (local Ollama, Cerebras, Groq)
Power Mode (Cmd+Alt+P)Autonomous multi-step agentsPowerful with tool support
ApplyExecuting code changesFast (local preferred)

Run a $0 local model for autocomplete. Use Claude Opus for Power Mode. No compromise.


Your Keys, Your Machine

  • API keys stored in your OS keychain
  • Network requests go directly from your machine to the provider
  • No Neural Inverse servers in the path
  • No telemetry on your prompts or responses
  • Works fully air-gapped with local providers

Get Started

# macOS / Linux
curl -fsSL https://neuralinverse.com/sh | bash

# Windows
irm https://neuralinverse.com/win | iex

Open Settings > Neural Inverse > LLM Providers. Enter your key. Start coding.

Copyright 2026 Neural Inverse Inc.


Was this page helpful?