API Overview
The Nexa Labs API provides access to our suite of 50+ AI models, including language models, specialized agents, and custom fine-tuned systems. Built on enterprise-grade infrastructure with 99.9% uptime SLA.
https://api.nexalabs.ai/v1All requests must include your API key in the Authorization header.
Quick Start
Get up and running in under 5 minutes. Here's a complete example to make your first API call.
1. Get your API Key
Sign up at nexalabs.ai and generate your API key from the dashboard.
2. Make your first request
Authentication
All API requests require authentication using an API key. Include your key in the Authorization header:
You can generate API keys from your dashboard. Keep your keys secure and never commit them to version control.
Available Models
We offer 50+ models across different categories. Each model is optimized for specific use cases.
🦄 Language Models
Nexa Unicorn 12B
Our flagship 12B parameter model. Best for general-purpose text generation.
12B params ChatNexa Unicorn 7B
Faster, lighter version. Great for real-time applications.
7B params FastNexa Unicorn 3B
Ultra-fast inference. Perfect for high-volume deployments.
3B params Ultra Fast📊 Marketing & Business
Market Genius Pro
Real-time multi-channel niche analysis with AI agents.
Marketing Multi-AgentCopywriter AI
Specialized in ad copy, emails, and social media content.
CopywritingSEO Content Pro
Generate SEO-optimized content with keyword integration.
SEOProduct Description AI
E-commerce product descriptions that convert.
E-commerceEmail Campaign Pro
Personalized email campaigns at scale.
EmailSocial Media Manager
Generate engaging posts for all platforms.
Social🏥 Medical & Healthcare
Neurai Health Pro
Medical diagnosis assistance and pharmaceutical research.
Medical HealthcareClinical Notes AI
Automated clinical documentation and note-taking.
ClinicalMedical Literature AI
Summarize and analyze medical research papers.
Research🤖 Agent Systems
Foundry Agent Orchestrator
Coordinate multiple AI agents for complex workflows.
Multi-AgentResearch Agent
Autonomous research assistant with web access.
ResearchData Analysis Agent
Analyze datasets and generate insights.
AnalyticsCode Generation Agent
Generate and debug code across multiple languages.
Coding💻 Code & Development
CodeGen Pro
Advanced code generation and completion.
CodingCode Review AI
Automated code review and bug detection.
Code ReviewDocumentation AI
Generate comprehensive code documentation.
Docs🎨 Creative & Content
Creative Writer AI
Stories, scripts, and creative content generation.
CreativeBlog Post Generator
Long-form blog content with SEO optimization.
BloggingVideo Script AI
Video scripts for YouTube, TikTok, and more.
Video🌍 Multilingual Models
Translation Pro
High-quality translation across 100+ languages.
TranslationMultilingual Chat
Chat in any language with context preservation.
Multilingual🔬 Specialized Models
Legal AI
Legal document analysis and drafting.
LegalFinancial AI
Financial analysis and report generation.
FinanceAcademic AI
Research paper writing and citation management.
AcademicCustomer Support AI
Intelligent customer support automation.
SupportCompletions API
Generate text completions using any of our models.
Endpoint
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model |
string | Yes | Model ID to use (e.g., "nexa-unicorn-12b") |
prompt |
string | Yes | The text prompt to generate from |
max_tokens |
integer | No | Maximum tokens to generate (default: 100) |
temperature |
float | No | Sampling temperature 0-2 (default: 1) |
top_p |
float | No | Nucleus sampling parameter (default: 1) |
stream |
boolean | No | Stream the response (default: false) |
Response
Embeddings API
Generate vector embeddings for semantic search and similarity.
Endpoint
Agents API
Deploy and manage intelligent AI agents for complex workflows.
Endpoint
Pricing
Simple, transparent pricing based on usage. No hidden fees.
| Model Category | Price per 1M tokens | Context Window |
|---|---|---|
| Nexa Unicorn 12B | $2.00 | 32K tokens |
| Nexa Unicorn 7B | $1.00 | 32K tokens |
| Nexa Unicorn 3B | $0.50 | 16K tokens |
| Marketing Models | $1.50 | 16K tokens |
| Medical Models | $3.00 | 32K tokens |
| Agent Systems | $0.10 per run | Varies |
| Embeddings | $0.10 | N/A |
Rate Limits
Rate limits are enforced to ensure fair usage and system stability.
| Plan | Requests per minute | Tokens per minute |
|---|---|---|
| Free Tier | 60 | 40,000 |
| Pro | 3,000 | 500,000 |
| Enterprise | Custom | Custom |
Error Codes
Standard HTTP status codes are used to indicate success or failure.
| Code | Meaning | Description |
|---|---|---|
| 200 | OK | Request succeeded |
| 400 | Bad Request | Invalid parameters |
| 401 | Unauthorized | Invalid API key |
| 429 | Too Many Requests | Rate limit exceeded |
| 500 | Internal Server Error | Server error |
Support
Need help? We're here for you.