This media is not supported in your browser
VIEW IN TELEGRAM
How to easily connect our API to your favorite app.
What is Gonka AI? How The REAL Decentralized AI Network Works
YouTube
What is Gonka AI? How The REAL Decentralized AI Network Works
Gonka-API.org is the direct, official access point to the Gonka decentralized AI network. In this video, we break down what makes Gonka the REAL decentralized AI protocol.
What you will learn in this video:
- Why the AI industry needs true decentralization…
What you will learn in this video:
- Why the AI industry needs true decentralization…
Meet Gonka API — your direct access to the REAL decentralized AI network. We made cheap, reliable inference incredibly easy for developers.
Current models and pricing (per 1M tokens):
- MiniMax-M2.7: $0.02 in / $0.03 out
- Kimi-K2.6: $0.02 in / $0.03 out
- Qwen3-235B: $0.015 in / $0.015 out
The Setup: 100% OpenAI-compatible. Just swap your API endpoint URL and you are live in minutes.
The Billing: Simple pay-as-you-go.
Stop overpaying for compute. Everyone gets 10M free tokens to start, but register through the link below to get an extra +10M bonus (20M total) to test it out:
gonka-api.org/?friend=PROMO
Current models and pricing (per 1M tokens):
- MiniMax-M2.7: $0.02 in / $0.03 out
- Kimi-K2.6: $0.02 in / $0.03 out
- Qwen3-235B: $0.015 in / $0.015 out
The Setup: 100% OpenAI-compatible. Just swap your API endpoint URL and you are live in minutes.
The Billing: Simple pay-as-you-go.
Stop overpaying for compute. Everyone gets 10M free tokens to start, but register through the link below to get an extra +10M bonus (20M total) to test it out:
gonka-api.org/?friend=PROMO
Important: for correct operation, replace the base address with this
Or go to the control panel, the new url is already placed there
https://hskyauefqcgbvgvxkluj.supabase.co/functions/v1/gonkaOr go to the control panel, the new url is already placed there
For high stability and response speed, use MiniMax. Now this is the most error- and hallucination-resistant model in the Gonka network.
Kimi and Qwen can at some points show 8192 output. This is due to the small number of their presence on the network servers.
This will be fixed in the coming months. And DeepSeek V4 will probably be added.
Rolling out new features and enjoying the prices.🏎 🏎
Kimi and Qwen can at some points show 8192 output. This is due to the small number of their presence on the network servers.
This will be fixed in the coming months. And DeepSeek V4 will probably be added.
Rolling out new features and enjoying the prices.
Please open Telegram to view this post
VIEW IN TELEGRAM
At the moment, some users have the opportunity to collect free millions of tokens.
We tried it as an experiment, but it turned out that users really like this gamification.
Therefore, we have opened it up to a larger number of active users.
Thank you to everyone who published materials about us on social networks, it's nice to read how Gonka API improves the capabilities of your products. ❤️
We tried it as an experiment, but it turned out that users really like this gamification.
Therefore, we have opened it up to a larger number of active users.
Thank you to everyone who published materials about us on social networks, it's nice to read how Gonka API improves the capabilities of your products. ❤️
Gonka-API.org hit a surge in traffic over the last few days and accounted for 12% of the entire decentralized AI network Gonka's utilization.
Thank you for using and connecting more and more applications to our provider.
Thank you for using and connecting more and more applications to our provider.
Awesome news for loyal users!
We have added a few features that you asked us about:
- web search (under the hood — Perplexity)
- image recognition emulation while there are no text-to-image models on the network
- normalization of the request when your agent sends incompatible with GonkaAI or OpenAI
- automatic replacement of the model, if selected temporarily offline
- hiding personal data from server and GPU holders
All these features are disabled by default. Enable and test them, we would be happy to receive your feedback.🤝
We have added a few features that you asked us about:
- web search (under the hood — Perplexity)
- image recognition emulation while there are no text-to-image models on the network
- normalization of the request when your agent sends incompatible with GonkaAI or OpenAI
- automatic replacement of the model, if selected temporarily offline
- hiding personal data from server and GPU holders
All these features are disabled by default. Enable and test them, we would be happy to receive your feedback.
Please open Telegram to view this post
VIEW IN TELEGRAM
Important: Requests to Kimi currently return a 429 rate limit error in 30% of cases, this is due to the fact that there are still relatively few servers with this model on board. We expect that improving the situation will take several days.
For now, we have increased the number of attempts to connect to the servers, which has reduced the number of errors to 10-15%.
For now, we have increased the number of attempts to connect to the servers, which has reduced the number of errors to 10-15%.
The current state of the AI model in the network is displayed on our dashboard, updated every minute, and historical data for the last hour can be viewed.
Also, GET /v1/models now returns
So that you can account for the model's operability in your app in advance and use a fallback or switch to another model in the network with a higher health status if necessary.
Also, GET /v1/models now returns
health: { success_rate: N }
So that you can account for the model's operability in your app in advance and use a fallback or switch to another model in the network with a higher health status if necessary.