OneProvider
Getting started

Get Support in Telegram

Stuck? Message OneProvider engineers in Telegram at @Oneproviderhelpbot. No tickets, no email queue. Here is what to send so we can fix it fast.

Real people in Telegram and in the cabinet's support chat. No ticket system: you talk to engineers, not Tier 1.

All models, capabilities, and prices Documentation index for AI agents: https://oneprovider.dev/docs/llms.txt Message @Oneproviderhelpbot Cabinet in Telegram

How to reach us

Message @Oneproviderhelpbot on Telegram or open “Support” in the web cabinet. The same channel handles billing, key issues, integration problems, and abuse reports.

When to use which channel

Reference data
NeedWhere
Issue a key, top up, check usageapp.oneprovider.dev or @oneprovider_robot — Cabinet & keys
Redeem a marketplace order codeBot: “Other” → “Activate code”. Website: “Balance” → “OP code”
"My request is failing"@Oneproviderhelpbot — include the request id, status code, and time-of-day in UTC
Leaked keyDelete it in the cabinet and issue a new one; contact support only if that fails
Refund / dispute@Oneproviderhelpbot — see Refund policy
Abuse report (someone is mis-using a key)@Oneproviderhelpbot — we act within hours, not days

What to include in a bug report

The faster you give us this, the faster we fix the issue:

  1. The endpoint path (e.g. POST /v1/messages) and the model name.
  2. The HTTP status code and the error.type string.
  3. Approximate timestamp in UTC.
  4. The first 8 characters of your key — not the whole key — so we can pull the request from logs.
  5. For client-side bugs: the tool (Cursor, Claude Code...) and its version.

Response time

We’re a small team in EU timezones. Median response is under 30 minutes during waking hours (07:00–23:00 UTC+0/+1), under 4 hours overnight. We don’t publish an SLA — this is the empirical baseline, not a contract.

Quick answers

Which base URL do I use?

Claude Code and Anthropic SDKs use https://api.oneprovider.dev. OpenAI SDKs and OpenAI-compatible clients use https://api.oneprovider.dev/v1. One key works behind both; the model list is on the models page ; rates are on the pricing page .

How do I authenticate?

Send the raw sk-… key in x-api-key or Authorization: Bearer: one of them, never both. Keep the key in an environment variable, not in a file that gets committed. More on authentication .

Where do I get a key?

Open your cabinet in the Telegram bot @oneprovider_robot or at app.oneprovider.dev, top up the balance and press “Issue a key”. Each key can carry its own spend limit. Cabinet & API keys .

What do 401, 404 and 429 mean?

401: the key is missing, mistyped or sent in the wrong header; paste the whole key without quotes or spaces. 404: usually a wrong base URL, for example a missing or doubled /v1. 429 with “Insufficient balance”: the cabinet balance or the key’s spend limit is used up, so top up instead of retrying; any other 429 is a rate limit, so wait for Retry-After. Details: error codes and troubleshooting .

Why do streams cut off or reset?

VPN and VLESS proxies often buffer SSE or break HTTP/2 negotiation. OneProvider has no regional restrictions and does not buffer streams, so turn the proxy off and retry.

Last updated: 2026-10-05 Found a bug? @Oneproviderhelpbot