AI Gateway

One API. Any Model.
Best Price.

Route to 10 AI providers and 35+ models from a single endpoint. OpenAI-compatible. SSE streaming. Prompt preprocessor saves 10–30% tokens before billing. Always 10% below OpenRouter.

10providers
35+models
300+edge locations
<80msp95 latency
0cold starts

One endpoint, any provider

Change the model field to switch providers. The API, response format, and streaming behavior stay identical.

The 4-pass prompt preprocessor runs automatically before every request — normalizing, trimming, and optionally compressing your messages before they hit the provider.

// TypeScript — works with any provider
const response = await fetch('https://app.neureus.ai/ai/chat', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer nr_your_api_key',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    // Switch providers by changing this string:
    model: 'claude-sonnet-4-6',
    // model: 'gpt-4o',
    // model: 'meta/llama-3.3-70b',  // free
    // model: 'gemini-3.5-flash',
    // model: 'deepseek-r1',
    messages: [{ role: 'user', content: 'Explain RAG in plain English' }],
    stream: true,  // SSE works across all providers
  }),
});
// Response: OpenAI-compatible SSE stream

All supported providers

Built-in models are always free. Paid models are priced 10% below OpenRouter.

AnthropicTop quality
  • claude-opus-4-8
  • claude-sonnet-4-6
  • claude-haiku-4-5
OpenAIMost popular
  • gpt-4o
  • gpt-4o-mini
  • o3
  • o4-mini
GoogleLong context
  • gemini-3.5-flash
  • gemini-3-flash-preview
  • gemini-3.1-flash-lite
Meta LlamaFree (built-in)
  • meta/llama-3.3-70b
  • meta/llama-3.1-8b
DeepSeekReasoning
  • deepseek-r1
  • deepseek-v3
MistralCode + edge
  • mistral-large-2411
  • mistral-small-3.1
CohereRAG-optimized
  • command-r-plus
  • command-r
QwenFree (built-in)
  • qwen/coder-32b

Always 10% below OpenRouter

The prompt preprocessor cuts token count before provider billing. You pay for what the model actually processes.

ModelOpenRouterNeureus (realtime)Neureus (batch)
GPT-4o$5.00/1M$4.50/1M$3.00/1M
Claude Sonnet 4.6$3.00/1M$2.70/1M$1.80/1M
Gemini 3.5 Flash$0.75/1M$0.675/1M~$0.45/1M
Llama 3.3 70B (built-in)$0.59/1MFreeFree
DeepSeek R1$0.55/1M$0.50/1M~$0.33/1M

Batch pricing applies to async jobs (POST /ai/batch). Built-in models always free on all plans.

Bring your own provider keys

On Scale plan and above: store your OpenAI or Anthropic API keys encrypted per tenant. Route through Neureus's gateway at your own rate — the preprocessor still saves 10–30% tokens on top of your direct pricing.

  • End-to-end encryption per tenant — keys never stored in plaintext
  • Rotate keys via POST /ai/providers/:provider/rotate — zero downtime
  • BYOK overlays global secrets — set once, use across all API calls
// Set your OpenAI key (Scale plan+)
await fetch('https://app.neureus.ai/ai/providers/openai', {
  method: 'PUT',
  headers: { 'Authorization': 'Bearer nr_key' },
  body: JSON.stringify({ apiKey: 'sk-your-key' }),
});

// Rotate (re-encrypts)
await fetch('https://app.neureus.ai/ai/providers/openai/rotate', {
  method: 'POST',
  headers: { 'Authorization': 'Bearer nr_key' },
});

What's included in the gateway

Multi-provider routing

Change providers by changing the model ID. claude-* → Anthropic, gpt-* → OpenAI, meta/* → built-in (free). Same API call, automatic dispatch.

SSE streaming

Set stream: true to get OpenAI-compatible Server-Sent Events from any provider — including Anthropic and Google — with a unified event format.

Prompt preprocessor

4-pass pipeline before every request: normalize → structure → trim (>6K tokens) → compress (opt-in). Cuts token count 10–30%.

Batch inference

Async batch jobs via OpenAI + Anthropic Batch APIs. 40% below realtime pricing. Webhook delivery on completion.

BYOK encryption

Bring your own OpenAI or Anthropic keys on Scale plan+. Encrypted per tenant. Rotate without downtime.

Edge delivery

300+ global locations. Zero cold starts. p95 latency <80ms globally.

Start routing to any provider in minutes

500 Neurons/month free. No credit card. Streaming, BYOK, and batch inference included.