JoinGonka Gateway — a full overview

JoinGonka Gateway is an intermediate layer between your application and the Gonka network. Architecture:

1. Your application sends a request to gate.joingonka.ai/v1/chat/completions (OpenAI format) or gate.joingonka.ai/v1/messages (Anthropic format).
2. Gateway accepts the request in either format, checks the API key and balance, and forwards it to the Gonka network.
3. Gonka network processes the request on one of the MLNodes where the selected model is deployed — MiniMax M2.7, DeepSeek V4 Flash, or GLM-5.3 Flash.
4. Gateway receives the response, counts the consumed tokens, deducts the balance, and returns the response to your application — in the same format the request was received (OpenAI or Anthropic).

Two API formats: Gateway supports both OpenAI Chat Completions API (/v1/chat/completions) and Anthropic Messages API (/v1/messages). This means tools like Cursor and LangChain work via the OpenAI format, and Claude Code connects directly via the Anthropic format — without proxies or converters.

Why is a Gateway needed if there is a direct Gonka API? The direct Gonka API requires a crypto wallet, signing GNK transactions, and understanding the blockchain. JoinGonka Gateway removes this complexity: you pay in a convenient currency (GNK, WGNK, USDT, fiat), receive a familiar OpenAI or Anthropic API format, and use the Dashboard for monitoring — without any knowledge of cryptocurrencies.

Technical stack: Fastify (Node.js), PostgreSQL, nginx. Gateway handles up to 1000 requests/sec, supports streaming (SSE in both formats), tool calling, and all parameters of OpenAI Chat Completions + Anthropic Messages API. Latency overhead is less than 50ms.

The whole process takes 2 minutes:

1. Sign up: go to gate.joingonka.ai/register. Email + password — a standard form.
2. Bonus: when you sign up, you automatically get 3M free tokens. That's enough for thousands of AI requests — plenty for testing and your first integrations.
3. Create a key: in the Dashboard → API Keys → Create Key. The key starts with jg-, for example jg-abc123def456. It's shown only once — save it.
4. First request: use the key in any OpenAI- or Anthropic-compatible client. For the OpenAI format, replace base_url with https://gate.joingonka.ai/v1. For the Anthropic format (Claude Code) — ANTHROPIC_BASE_URL=https://gate.joingonka.ai.

Ready-made guides for popular tools: Cursor, Claude Code, Aider, Continue.dev, Cline, LangChain, n8n, Open WebUI, LibreChat. Code examples (curl, Python, TypeScript) are in the API quickstart.

Dashboard: your account shows your current token balance, request history, daily spend, API keys, and referral link. It's a full-fledged CRM for managing your AI spend.

The same open models distributed by the decentralized Gonka network are also available on standard inference platforms—for example, OpenRouter. The difference is how much they charge for them. Let's compare the price per 1M tokens for the same models:

The same model—at ~6—58 times cheaper. JoinGonka Gateway provides MiniMax-M2.7, DeepSeek-V4-Flash (380K context—the second longest in the network after 390K for GLM-5.3-Flash), and GLM-5.3-Flash for ~$0.0069 input and ~$0.021 output per 1M tokens (output is 3x more expensive—as with other providers). On standard platforms, the same model weights cost ~6—58 times more: the reason is the architecture—in Gonka, inference is paid for by miners via Proof of Useful Work, not by data center margins.

Not just price. JoinGonka Gateway provides both API formats—OpenAI (/v1/chat/completions) and Anthropic (/v1/messages), so Claude Code connects directly via the native Anthropic format. Plus native tool calling, a Dashboard with analytics, flexible payment (GNK 0%, WGNK 1%, USDT 5%, fiat), and a referral program (10% L1 + 3% L2).

Eight key advantages:

1. The cheapest OpenAI + Anthropic compatible API: $0.0069/1M tokens—~720 times cheaper than OpenAI GPT-5.5. For most tasks, the difference in quality is unnoticeable, but the cost difference is radical.
2. Two API formats—OpenAI and Anthropic: /v1/chat/completions (OpenAI) and /v1/messages (Anthropic)—both work with a single key. Cursor, LangChain, and OpenAI SDK use the OpenAI format. Claude Code uses the Anthropic format directly, without proxies. No competitor offers this.
3. Native tool calling: all network models support function calling in both formats—OpenAI and Anthropic. Agents, chains, and automation—everything works reliably.
4. Free start: 3M tokens upon registration. This is enough for weeks of testing and your first integrations—without payment.
5. Flexible payment: GNK (0% fee), WGNK from Ethereum (1%), USDT (5%), fiat via On-Ramp. No need to understand cryptocurrencies—you can pay by card.
6. Referral program: 10% of spending by referred users (L1) + 3% from their referrals (L2). Share your link and earn tokens.
7. Dashboard and analytics: a full-featured CRM—balance, spending, request history, API keys. Everything in one interface.
8. Full ecosystem compatibility: works with any OpenAI-compatible client (Cursor, n8n, LangChain) and Anthropic-compatible client (Claude Code)—without modifications.

JoinGonka Gateway billing works in GNK tokens (internal unit):

• Top-up GNK: 0% fee. You send GNK to the Gateway address, the balance is credited instantly.
• Top-up WGNK: 1% fee. For GNK on the Ethereum network — the transfer is credited automatically.
• Top-up USDT: 5% fee. Pay with USDT (via OxaPay), and the Gateway converts it to GNK automatically. 5% is a convenience fee (no Gonka crypto-wallet needed).
• Top-up fiat: via On-Ramp (card → USDT → GNK). The fee depends on the On-Ramp provider.

Platform fee: a 10% fee is applied to the base inference cost on the Gonka network. This fee is already included in the final price of ~$0.0069/1M tokens. The base network cost is ~$0.0046/1M, with the fee — ~$0.0069/1M. The fee covers Gateway infrastructure costs (servers, DB, monitoring).

How usage is calculated: every API request (both via OpenAI-format and Anthropic-format) consumes tokens from a unified balance. The Gateway counts prompt_tokens (input) + completion_tokens (output) and deducts them from the balance. Cost: $0.0069 per 1M tokens (~0.003 GNK at the current exchange rate). One key, one balance — for both API formats.

Tool calling: function calls (tools) also consume tokens — function definitions are added to the prompt. A typical tool calling request consumes 1.5-3x more tokens than a standard one — but at $0.0069/1M, it is still negligible.

Referral program: every user receives a unique referral link in the Dashboard. When an invited user spends tokens, you receive 10% of their spend (L1). If your referral also invites people, you receive 3% of their spend (L2). Referral rewards are credited in GNK tokens to your balance.

Transparency: all transactions are visible in the Dashboard — top-ups, debits, referral earnings. The API returns a usage object with every response — you always know how many tokens the request consumed.

Model parameters: context window — 200K tokens for MiniMax M2.7, 380K for DeepSeek V4 Flash, and 390K for GLM-5.3 Flash. Maximum response length — up to 8192 tokens (DeepSeek V4 Flash — up to 32768; default without max_tokens is 1500). Supported API parameters: model, messages, max_tokens, temperature, tools, tool_choice, stream.