ThunderPeak Community

Guides, model-selection tips, billing answers and real human support — everything you need to get more out of one API key. Whether you are shipping a hobby project or running an agent fleet in production, this is where the practical details live.

Where the community lives

Telegram

Announcements, model updates and fast answers. Support replies in your language.

Join @thunderpeak_support →
Email

Billing questions, invoices, compliance and account issues.

[email protected] →
Console

Keys, token-level usage, per-key limits and full request history.

Open the console →

Guides & resources

Get connected in one line

Change the base URL and keep your existing SDK.

One-line setup →
API reference

Endpoints, streaming, tool calling and protocol compatibility.

Documentation →
Choosing a model

How to pick between frontier and mainstream models, and how token billing works.

Learn hub →
Model catalogue

Live list of available models with per-token rates.

Browse models →

Who builds on ThunderPeak

Frequently asked questions

How do I get started?

Create an account in the console, generate an API key, and point any OpenAI-compatible or Anthropic-compatible client at the gateway base URL. New accounts get $2.50 of free usage so you can test models before paying.

Which models can I call with a single API key?

One key covers the Claude, GPT, DeepSeek, Qwen, Kimi and GLM families. Requests are normalised across protocols and routed to the fastest healthy upstream for the model you ask for.

How does pricing work?

Claude and GPT are sold at 66% of official rates, DeepSeek and Kimi K3 at 88%, GLM-5.3 at 80% and GLM-5.2 at 70%, with Qwen at official rates. These are standing prices, not launch promotions — the discount you see today is the discount we intend to keep.

Do credits expire?

No. Credits are prepaid and never expire. There is no subscription, no seat count and no minimum monthly commitment.

How do I top up?

Top up with USDT on Tron (TRC-20), BSC or Solana from $10. Every request is metered at published per-model token rates, with input, output, cache-write, cache-read and thinking tokens accounted for individually.

Can I use Claude Code, Codex CLI or Cursor?

Yes. The gateway speaks both OpenAI-compatible chat completions and Anthropic-compatible messages, so Claude Code, Codex CLI, Cursor, Cherry Studio, VS Code extensions and the official SDKs all work after changing only the base URL.

Is there a reseller or agency program?

Yes — wholesale rates and hundreds of client keys managed from one balance. See the reseller program for details.

Talk to a human

Support is human and responsive. Reach us on Telegram @thunderpeak_support or by email at [email protected] — we reply in your language.

Create API key