OpenAI
import OpenAI from 'openai'

const HICAP_API_KEY = process.env.HICAP_API_KEY

const client = new OpenAI({
  baseURL: 'https://api.hicap.ai/v1',
  apiKey: HICAP_API_KEY,
  defaultHeaders: { "api-key": HICAP_API_KEY },
})

const response = await client.chat.completions.create({
  model: 'gpt-5.2',
  messages: [
    { role: 'user', content: 'Hello, GPT!' }
  ],
})
Works with your tools

Integrate in minutes

Hicap works with any OpenAI-compatible tool. Just change your base URL and start saving.

OpenAI SDK

Any OpenAI-compatible app

CLI

Claude Code, Aider & more

VS Code

Cline, Copilot & extensions

Trusted by teams at

ClineGPTHiveflowMintachu
Pacer

Real-World Savings Examples

Solo Developer

Up to 25% off

Full-time AI-assisted coding across projects

Project Apps Usage
Web Applications$1,711$1,284
40% of total spend
Dev Tools & CLIs$1,070$802
25% of total spend
APIs & Backends$642$481
15% of total spend
Automation Scripts$513$385
12% of total spend
Side Projects$342$257
8% of total spend
Usage~4B tokens/mo
Direct$4,278/mo
Hicap$3,209/mo
Annual Savings$12,828/yr

Startup Team

Up to 25% off

10 developers + product AI usage for rapid development

Product Usage
Code Generation$23,740$17,805
35% of total spend
Rapid Prototyping$16,957$12,718
25% of total spend
AI Product Features$12,209$9,157
18% of total spend
Automated Testing$8,818$6,613
13% of total spend
CI/CD & DevOps$6,105$4,579
9% of total spend
Usage~5B tokens/mo
Direct$67,829/mo
Hicap$50,872/mo
Annual Savings$203,484/yr

Enterprise Team

Up to 25% off

Large-scale AI development with high-volume usage

Development Usage
Code Generation$300,000$225,000
40% of total spend
Code Review & QA$187,500$140,625
25% of total spend
Documentation$112,500$84,375
15% of total spend
Data Pipelines$90,000$67,500
12% of total spend
Internal Tooling$60,000$45,000
8% of total spend
Usage~5B tokens/day
Direct$750,000/mo
Hicap$562,500/mo
Annual Savings$2,250,000/yr

Swipe to see more examples

Features

Reserved Throughput.
Pay-as-you-go Commitments.

We buy reserved GPU capacity in bulk, then let you tap into it on-demand.
You get the speed of provisioned throughput at a fraction of the cost.

Up to 25% lower costs

Access the same models at a fraction of pay-as-you-go pricing through reserved GPU capacity.

Fast & reliable inference

Provisioned throughput delivers consistent performance for your workloads. No cold starts, no throttling.

All major models

Browse the reserved capacity catalog—GPT-5.2, Claude 4 Sonnet, Gemini 3.0 Flash and more. Contact our team to get started.

View catalog →

Built-in usage analytics

Track token usage, costs, and latency across all models. See exactly where your AI budget goes.

Drop-in replacement

Works with curl, OpenAI SDK, or any OpenAI-compatible tool. Just change the base URL.

Enterprise-grade reliability

Your requests are load-balanced across multiple providers for redundancy and high availability.

Need reserved capacity or enterprise pricing?

Get dedicated GPU throughput, volume discounts, and priority support for your team. We'll tailor a plan to your usage.

Contact SalesOr get started free →