One API for leading AI models
Access leading AI models through one OpenAI-compatible API, with unified keys, usage tracking, billing in USD, and reliable routing.
Ship in minutes
Already using the OpenAI SDK? Change base_url and api_key — no other code changes required.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.boostrail.com/v1",
)
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_API_KEY",
baseURL: "https://api.boostrail.com/v1",
});
const completion = await client.chat.completions.create({
model: "deepseek-v4-pro",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);curl https://api.boostrail.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Hello"}]
}'Built for production
One unified API
One API key calls every model in the catalog. OpenAI-compatible, with streaming supported.
Unified billing
Prepaid credits in USD, transparent per-token pricing, and usage, statements, and exports in one console.
Reliable routing
The platform monitors upstream channels continuously and fails over automatically when one degrades.
Bring your own keys
Connect your own provider API keys: inference runs on your provider accounts and contract prices, with the platform as automatic fallback.
Video generation
Generate video through the async /v1/videos task API, billed per second of output — failed or cancelled tasks are never charged.
Built for coding agents
Native endpoints for Claude Code, Codex CLI, Cline, and more — better token prices, cache reads at 10% of input, no cache-write surcharge.
Three steps to start
Top up credits
Pay by card through Stripe, or by Wise transfer (USD). One balance covers every model.
Create a key and call
Point base_url and api_key at the gateway and call every model in the catalog.
Frequently asked questions
Does the OpenAI SDK work?
Yes. Change base_url, api_key, and model — the official Python and Node.js SDKs, and any HTTP client, work as-is.
Which models are available?
45+ models from providers including Anthropic (Claude), OpenAI (GPT), Google (Gemini), DeepSeek, GLM, xAI (Grok), Kimi (Moonshot), Qwen (Alibaba), and MiniMax, plus video generation models billed per second. The full list with prices is on the Models page and grows as providers are onboarded.
Can I bring my own provider API keys?
Yes — BYOK lets you store your own provider keys so inference runs on your provider accounts and contract prices, with the platform as automatic fallback. The free plan includes 1,000,000 BYOK requests per month with up to 3 providers, and needs no top-up. See the BYOK page.
How does billing work?
Accounts are prepaid. Credits are purchased in USD and consumed per request at the per-token prices shown in the console. No subscription fee.
Which payment methods are supported?
Card payments run through Stripe Checkout, which accepts major credit and debit cards. Wise transfer (USD) is also supported: transfer to our Wise receiving account, declare it under Recharge in the console, and credits post after we match the incoming funds.
Is streaming supported?
Yes. Set stream=true and responses arrive in the OpenAI streaming format.