One endpoint for
every frontier model

Set up in 3 steps

Under 5 minutes from zero to first API call.

Drop-in replacement

Just change two lines. Everything else stays the same.

from openai import OpenAI

client = OpenAI(
    api_key="ng-your-key",
    base_url="https://api.nexgate.app/v1"
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Built for production agents

Everything your coding agent or orchestration system needs.

Model quick-reference

Paste the model ID directly into your tool config. Pricing per million tokens.

# NexGate — OpenAI-Compatible API Gateway

## Connection

Base URL:       https://api.nexgate.app/v1
API Key prefix: ng-{your-key}
Protocol:       OpenAI Chat Completions API (drop-in replacement)

## Quick Start

```python
from openai import OpenAI
client = OpenAI(
    api_key="ng-your-key",
    base_url="https://api.nexgate.app/v1"
)
```

```typescript
import OpenAI from 'openai';
const client = new OpenAI({
  apiKey: 'ng-your-key',
  baseURL: 'https://api.nexgate.app/v1',
});
```

## Available Models

- gpt-5.5
- gpt-5
- gpt-5.4-mini
- gpt-5.4-nano
- gpt-4.1
- gpt-4.1-mini
- gpt-4.1-nano
- gpt-4o
- o4-mini
- deepseek-v4-pro
- deepseek-v3.2
- deepseek-v4-flash
- kimi-k2.6
- grok-4-3
- grok-4-20-reasoning
- grok-4-1-fast-reasoning
- llama-4-maverick
- llama-4-scout

## Multi-Model Access

NexGate exposes all models behind one OpenAI-compatible endpoint. Switch by changing the "model" parameter — no code changes, no re-auth.

Recommended defaults by task:
- gpt-5.5            → flagship quality for coding, planning, and code review
- deepseek-v4-pro    → frontier DeepSeek with enhanced reasoning
- gpt-5.4-mini       → balanced default when you want lower cost
- deepseek-v3.2      → efficient coding and chat
- grok-4-3           → latest Grok 4.3 frontier model
- kimi-k2.6          → very long context (256K tokens)
- llama-4-maverick   → open model, 512K context

## Billing

NexGate uses prepaid credits (1 credit = $1 USD).
- Credits never expire
- No subscriptions, no monthly charges
- Requests deduct exact token cost at time of use
- Dashboard: https://dashboard.nexgate.app
- Top-up at: https://nexgate.app/pricing

There is no risk of unexpected charges beyond your credit balance.

## Streaming

All chat completion models support SSE streaming via OpenAI's stream parameter.

```python
stream = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Write a story"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
```

## Getting Started

1. Sign up at https://nexgate.app/sign-up — you receive $5 free credits, no card required
2. Generate an API key at https://dashboard.nexgate.app
3. Set base_url / baseURL to https://api.nexgate.app/v1
4. Replace your OpenAI API key with your NexGate key (starts with "ng-")

Your existing OpenAI SDK code works without modification.