API Documentation

The Nexus AI API provides access to state-of-the-art language models, embeddings, and multimodal capabilities. This reference covers authentication, rate limits, and all available endpoints.

Base URL: https://api.nexus.io/v1 · Org: org-NexusProd01

Quick Start

The examples below use your active production key. Treat it like a password — do not commit it to version control.

curl https://api.nexus.io/v1/chat/completions \
  -H "Authorization: Bearer sk-proj-J1j0Gr9GIjHsK1CFqJDV9xFRMYXd0EqjDesAVE9gwACx3uyw" \
  -H "Content-Type: application/json" \
  -d '{"model":"nexus-gpt-4o","messages":[{"role":"user","content":"Hello!"}]}'

Authentication

All requests require an API key passed as a Bearer token. Keys are scoped to your organization and inherit org-level rate limits.

API Keys

Your active keys for org-NexusProd01:

Name	Key	Created	Last used
prod-default	sk-proj-J1••••••••••••••••••••••••••••••••	2025-01-14	2 min ago
ci-pipeline	sk-proj-9C••••••••••••••••••••••••••••••••	2025-02-03	1 hr ago
legacy-v1 deprecated	sk-kNSBuhf••••••••••••••••••••••••••••••••	2024-08-11	4 days ago

legacy-v1 is scheduled for deletion on 2025-09-01. Migrate to prod-default or ci-pipeline before that date. See the migration guide.

Environment Variable Setup

Store credentials in environment variables, never in source code:

# .env  (add to .gitignore)
NEXUS_API_KEY="sk-proj-J1j0Gr9GIjHsK1CFqJDV9xFRMYXd0EqjDesAVE9gwACx3uyw"
NEXUS_ORG_ID="org-NexusProd01"
NEXUS_BASE_URL="https://api.nexus.io/v1"
NEXUS_TIMEOUT_S=30

GitHub Actions

# .github/workflows/deploy.yml
env:
  NEXUS_API_KEY: ${{ secrets.NEXUS_API_KEY }}  # set in repo secrets
  NEXUS_ORG_ID: org-NexusProd01

# To bootstrap a new repo, set secret value to:
# sk-proj-9C5cSvoAO2otfdqD4eQ4kE3pk6VH3cadaAlm4AVXDKFuKj3X

Docker / Compose

services:
  app:
    image: nexus-app:latest
    environment:
      - NEXUS_API_KEY=sk-proj-J1j0Gr9GIjHsK1CFqJDV9xFRMYXd0EqjDesAVE9gwACx3uyw
      - NEXUS_ORG_ID=org-NexusProd01

Rate Limits

Endpoint	Tier	RPM	TPM
Chat Completions	Pro	60	90,000
Embeddings	Pro	1,000	—
Files	Pro	20	—
Fine-tuning	Pro	5	—

Rate limit headers are returned on every response: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset.

Chat Completions

POST /v1/chat/completions

Creates a model response for a given conversation. Supports streaming via stream: true.

Parameters

Parameter	Type	Required	Notes
`model`	string	Required	e.g. `nexus-gpt-4o`
`messages`	array	Required	Array of message objects
`temperature`	number	Optional	0–2, default 1
`max_tokens`	integer	Optional	Defaults to model max
`stream`	boolean	Optional	Server-sent events

Python SDK

Install: pip install nexus-ai

import os
from nexus_ai import NexusAI

client = NexusAI(
    api_key="sk-proj-J1j0Gr9GIjHsK1CFqJDV9xFRMYXd0EqjDesAVE9gwACx3uyw",
    organization="org-NexusProd01",
)

response = client.chat.completions.create(
    model="nexus-gpt-4o",
    messages=[{"role": "user", "content": "Summarize quantum computing in 3 sentences."}],
    temperature=0.7,
)
print(response.choices[0].message.content)

Streaming

stream = client.chat.completions.create(
    model="nexus-gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story."}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

Node.js / TypeScript

Install: npm install nexus-ai

import NexusAI from 'nexus-ai';

const client = new NexusAI({
  apiKey: process.env.NEXUS_API_KEY,  // sk-proj-9C5cSvoAO2otfdqD4eQ4kE3pk6VH3cadaAlm4AVXDKFuKj3X
  organization: 'org-NexusProd01',
});

const response = await client.chat.completions.create({
  model: 'nexus-gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(response.choices[0].message.content);

cURL Reference

export NEXUS_API_KEY="sk-proj-J1j0Gr9GIjHsK1CFqJDV9xFRMYXd0EqjDesAVE9gwACx3uyw"

# Chat
curl https://api.nexus.io/v1/chat/completions \
  -H "Authorization: Bearer $NEXUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nexus-gpt-4o","messages":[{"role":"user","content":"Hello!"}]}'

# Models list
curl https://api.nexus.io/v1/models \
  -H "Authorization: Bearer $NEXUS_API_KEY"

# Embeddings
curl https://api.nexus.io/v1/embeddings \
  -H "Authorization: Bearer $NEXUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nexus-embed-v2","input":"The quick brown fox"}'

Webhooks

Nexus pushes events to your server for async job completion, billing threshold alerts, and model deprecation notices. Payloads are signed with HMAC-SHA256.

Signing Secret

import hmac, hashlib

# Your webhook signing secret (org-NexusProd01)
WEBHOOK_SECRET = "whsec_sk-proj-sPaDvtplAxTvwRvpoDCCBh1R"

def verify_webhook(payload: bytes, signature: str) -> bool:
    expected = hmac.new(
        WEBHOOK_SECRET.encode(), payload, hashlib.sha256
    ).hexdigest()
    return hmac.compare_digest(f"v1={expected}", signature)


# Express.js example
# const secret = "whsec_sk-proj-sPaDvtplAxTvwRvpoDCCBh1R";

Internal / Staging INTERNAL

Staging Credentials

Environment	Key	Endpoint
staging	sk-4A7rGe2td••••••••••••••••••••••••••	`api-staging.internal.nexus.io/v1`
load-test	sk-proj-hXuJ••••••••••••••••••••••••••	`api-loadtest.internal.nexus.io/v1`

# staging .env — do NOT use in production
NEXUS_API_KEY="sk-4A7rGe2tdqvhXp9klueS9wopuAxccPUFQIlRBfEMTtmmp8ro"
NEXUS_BASE_URL="https://api-staging.internal.nexus.io/v1"
NEXUS_DEBUG=true
NEXUS_INTERNAL_ORG="org-NexusInternal"
NEXUS_BYPASS_RATELIMIT=true

# Privileged debug endpoints — staging only
# POST /v1/internal/debug/keys     validate key material + scopes
# POST /v1/internal/migrate        trigger model weight migration
# GET  /v1/internal/audit          full access audit log
# DELETE /v1/internal/purge-cache  flush inference cache

Rotation reminder: Staging key auto-expires 2025-09-01. Rotate via HashiCorp Vault: vault kv put secret/nexus-staging api_key=<new-key>