Frequently asked questions

Yes. Change base_url, api_key, and model — the official Python and Node.js SDKs, and any HTTP client, work as-is.

68 models from 13 labs, including Anthropic (Claude), OpenAI (GPT), Google (Gemini), DeepSeek, GLM, xAI (Grok), Kimi (Moonshot), Qwen (Alibaba) and MiniMax: 56 text models, plus image models billed per image and video models billed per second. The full list with prices is on the Models page.

Yes. Set stream=true. Each API format streams in its own standard events: OpenAI chunks on /v1/chat/completions, Responses events on /v1/responses, and Anthropic events on /v1/messages.

With stream=true, servers send SSE keep-alive lines and chunks whose delta may be empty — this is normal in the OpenAI streaming format. Read events until data: [DONE] and concatenate the non-empty delta contents.

Accounts are prepaid. Credits are purchased in USD and consumed per request at the per-token prices shown in the console. No subscription is required; BYOK plans are optional.

Card payments run through Stripe Checkout, which accepts major credit and debit cards. USDT goes through a hosted crypto checkout and posts automatically once the payment confirms. 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.

Where applicable, tax is calculated by Stripe Tax at checkout based on the billing address, shown before payment, and recorded on the order. Card top-ups carry a payment processing fee (5.5%, or $0.80 minimum, shown before payment); credited amounts always equal the principal. USDT top-ups carry a 1% fee ($0.10 minimum). The minimum card top-up is $5. Business customers can add tax IDs.

Requests are rejected without creating a negative balance. When the balance can't cover a full-length response and the request doesn't set max_tokens, the output limit is lowered to what the balance covers and the response ends with finish_reason "length". Set a balance alert in the console to get warned early.

If a streaming request is closed before it completes, it is billed for the usage the provider reports for that request. This can include reasoning tokens and output the provider finishes generating shortly after the connection closes. If the provider does not report usage in time, usage is estimated: for a model that produced reasoning, as the input plus the full output allowance reserved for the request (max_tokens, or the default allowance when none is set); otherwise, from the text generated. Estimates never exceed the amount reserved for the request. If the provider fails mid-stream, the request is not charged.

Purchased credits do not expire while the account remains active. Promotional or trial credits may carry an expiry date, which is shown when they are granted.

Accounts that sign up in the console with a major email provider (Gmail, Outlook, iCloud, QQ, 163 and others) or a company email on Google Workspace, Microsoft 365 or a similar business mail service, and verify it, receive $1 in trial credit, once per account. Trial credit is valid for 7 days, is offered while this month's trial budget lasts, and unused trial credit expires after the 7 days. After that, top up or use your own keys with the free BYOK plan.

Purchased credits are non-refundable, in line with common practice for prepaid API platforms. Please top up according to your actual usage; where consumer law grants non-waivable rights, those rights are unaffected.

First check the order status under Billing; credits post automatically after payment confirmation, usually within a minute. Bank-transfer top-ups post after our review of the bank statement. If it still looks wrong, open a ticket with the order ID and we will reconcile it against payment records.

An invoice is issued automatically for every successful top-up. Open Recharge → transaction records → top-up orders in the console: the invoice column on each order row views or prints it (printing saves a PDF; Stripe-issued invoices download from the same place). Set the invoice header — name, tax ID, address — under the Wise transfer section of the Recharge page.

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.

Requests switch to the platform's paid lines automatically at the published platform prices — no hidden markup — and your application keeps running. The monthly quota resets on the 1st of the month (UTC); models that run only on your own key pause until then.

The console provides a usage overview, per-model details, request logs, and CSV exports, filterable by project, API key, and model.

When the route serving a request fails, the request is retried on another route of the same model before any data reaches you. Requests that fail are not charged. The exact rules are on the Errors and failover page under Docs.

Each organization can send up to 600 requests per minute, and each API key can carry its own per-minute and daily / monthly spend limits, set in the console. If a workload needs a higher organization limit, open a ticket describing the traffic pattern and we will review it.

The platform stores only an irreversible digest of each key, never the plaintext. Save it to a secrets manager when you create it.

Disable it in the console — it takes effect immediately — and create a replacement.

Request and response contents are used only to serve the call; usage metadata is kept for billing. See the Privacy Policy.

Open a ticket in the console, or email support@boostrail.com.

Yes. For enterprise procurement, custom agreements, or reseller arrangements, email support@boostrail.com and we will follow up.