Open-source LLMs, production-ready API

Open-source LLM inference
at a low cost

TrustedRails gives you an OpenAI-compatible API for powerful open-source models. Standard billing in USD, your data stays under your control.

Why developers choose TrustedRails

Powerful open-source models through a familiar API. No infrastructure to manage.

OpenAI-compatible API

Just change the base_url in any OpenAI SDK. Supports Python, JS, and other clients.

Simple USD billing

Pay as you go with a card. No commitments, no minimum spend. Clear per-token pricing.

Your data stays yours

Unlike major providers, your prompts and completions are not used for training. No vendor sees the full picture.

No vendor lock-in

Open-source models, standard API. Switch to or from TrustedRails in two lines of code.

Start in 3 steps

From sign-up to first inference in under a minute.

Create an account

Generate an API key

In the dashboard, create a key for your application or environment.

Send requests

Point any OpenAI-compatible client to our API and start inferring.

Works with any OpenAI client

Just change two lines — the base URL and API key. Your existing code, tools, and frameworks keep working.

Python

Use the official openai package. Works with LangChain, LlamaIndex, and any OpenAI-compatible framework.

from openai import OpenAI

client = OpenAI(
    base_url="https://proxy.trustedrails.com/v1",
    api_key="tr-prx-YOUR_KEY_HERE"
)

response = client.chat.completions.create(
    model="Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
    messages=[{"role": "user", "content": "Hello!"}]
)

JavaScript / TypeScript

Use the official openai npm package. Works with Node.js, Deno, Bun, and browser environments.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://proxy.trustedrails.com/v1",
  apiKey: "tr-prx-YOUR_KEY_HERE",
});

const response = await client.chat.completions.create({
  model: "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8",
  messages: [{ role: "user", content: "Hello!" }],
});

Also works with Cursor, Continue, LibreChat, and any tool that supports a custom OpenAI endpoint.

Get your API key

Inference pricing

Run open-source models at rock-bottom token prices — with your USD rate locked in when you top up.

Model / Provider	Input (per 1M tokens)	Output (per 1M tokens)
OpenAI GPT-5	$1.25	$10.00
Claude 4.5 Sonnet	$3.00	$15.00
TrustedRails · MiniMax M2	$0.30	$0.30
TrustedRails · Kimi K2	$0.35	$0.35

*Prices may fluctuate based on GPU supply and demand. Shown for illustrative purposes.

Accepted payment methods

and others

For developers

Works with your favorite tools

Point any OpenAI-compatible client to TrustedRails and get instant access to open-source models at low cost. No custom SDKs, no code rewrites.

Any OpenAI SDK
Python, JavaScript, Go — just change base_url and api_key.
AI-powered tools
Cursor, Continue, LibreChat, and any app with a custom OpenAI endpoint setting.
Frameworks
LangChain, LlamaIndex, and other libraries that use the OpenAI API format.

See code examples Read the docs

Quick start

1 Sign up — account in 30 seconds
2 Create a key in the dashboard
3 Change base_url to https://proxy.trustedrails.com/v1 and start

Get a free API key

Your data never reaches model vendors

When you use OpenAI or Anthropic directly, your prompts pass through their infrastructure. With TrustedRails, inference runs on distributed independent operators — no model vendor sees your data.

End-to-end encryption is on our roadmap — so that no one, not even infrastructure operators, can access your data in transit.

Start using cheap inference now

Open-source models, transparent pricing, your data under your control.

Already have an account? Sign in

Open-source LLM inference at a low cost