AI infrastructure

One API.
Every frontier model.

Nexra gives your team a single, OpenAI-compatible endpoint for large language models. One key, one bill, one dashboard — switch model families without rewriting code.

Get an API key Read the quickstart

curl https://api.nexra.art/v1/chat/completions \
  -H "Authorization: Bearer $NEXRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nexra-standard","messages":[{"role":"user","content":"Hello"}]}'

OpenAI-compatible schema. Point any existing SDK at the base URL. The legacy host api.mintapi.cc remains available.

What Nexra does

Unified endpoint

One request format across model families. Keep your OpenAI SDK, change the base URL.

Routing & fallback

Send each request to the model that fits the job, with automatic fallback when a provider degrades.

Spend control

Per-key budgets, rate limits and usage logs, so a runaway script cannot run up an unbounded bill.

What we operate

Nexra runs three lines of work under one company: data processing, cloud hosting, and AI applications.

Data processing

Ingesting, normalising and routing API traffic, metering token usage, and producing the usage reports and billing records behind every account.

Cloud hosting

Managed API endpoints on cloud infrastructure with health checks, rate limiting and per-key isolation — nothing for customers to install or operate.

AI applications

Building and running applications and integrations on top of language-model APIs: chat, summarisation, extraction and agent-style workflows.

Who it is for

AI product teams

Ship features on top of multiple models without integrating each provider separately.

Independent developers

Prototype and scale on one account, with usage-based billing and no monthly minimum.

Agencies

Give each client its own key, budget and usage report on the same account.

Pricing

Usage-based. You prepay credits, they are drawn down per token, and you top up when you need more. No monthly minimum, no seat fees.

Starter

For prototypes

Pay-as-you-go credits
Standard rate limits
Email support

Growth

For production apps

Higher concurrency
Per-key budgets & alerts
Usage exports

Scale

For high volume

Volume rates
Dedicated capacity options
Priority support

Per-token rates vary by model family and are listed in the dashboard before you commit. Contact us for volume pricing.

Quickstart

Send a request from the contact form to get an API key.
Set base_url to https://api.nexra.art/v1.
Call it with the OpenAI SDK — the schema is identical.

Full request/response reference: API documentation.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_NEXRA_KEY",
    base_url="https://api.nexra.art/v1",
)

resp = client.chat.completions.create(
    model="nexra-standard",
    messages=[{"role": "user", "content": "Summarise this changelog."}],
)
print(resp.choices[0].message.content)

Operating entity and policies

Nexra is operated by Nexra LLC, a limited liability company registered in the United States. Access is governed by our Terms of Service, Privacy Policy and Acceptable Use Policy.

Nexra is an independent service. It is not affiliated with, endorsed by, or sponsored by any model provider. Model names referenced by customers remain the property of their respective owners.

Contact

Tell us what you are building and we will send an API key and current rates.

Email [email protected]
Support [email protected]
Hours Mon–Fri, 09:00–18:00 (UTC+8)

One API.Every frontier model.