Channel
@GonkaAPI
On this record: Topic · Growth · Engagement · What this channel posts · Posts · Cite this entry
320subscribers
+185 since we began measuring on 7 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1003487233351 |
|---|---|
| Type | Channel |
| Username | @GonkaAPI |
| Created | 12 January 2026 — measured — dated from the channel’s first post |
| First recorded | 8 August 2026 |
| Last confirmed live | 8 October 2026 |
| Measurements held | 10 |
| Confirmed unchanged | 1 time, most recently 8 October 2026 |
| On Telegram | t.me/GonkaAPI |
Technology — a classification, not a measurement. An on-box language model (Qwen3.6-35B-A3B-FP8, prompt version 1) read this channel’s own recent posts on 24 September 2026 and assigned it the closest of 31 fixed categories, at 99% confidence. This is a model’s judgement about what the channel is likely to be about, not a fact this register measured the way a subscriber count or a view count is measured — it can be revised on a later pass, and it carries no weight anywhere else on this page. How this classification works, and why it has no browse page of its own yet.
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 8 Oct 2026, 11:02 | 320 | +59 |
| 28 Sept 2026, 07:37 | 261 | +51 |
| 15 Sept 2026, 07:58 | 210 | +6 |
| 8 Sept 2026, 10:37 | 204 | +8 |
| 29 Aug 2026, 21:07 | 196 | +18 |
| 21 Aug 2026, 23:28 | 178 | +31 |
| 14 Aug 2026, 09:38 | 147 | +11 |
| 8 Aug 2026, 23:31 | 136 | no change |
| 7 Aug 2026, 23:28 | 136 | +1 |
| 7 Aug 2026, 19:42 | 135 | first reading |
17 posts held, back to 12 January 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 17 posts for this entry, the most recent from 4 August 2026. An engagement rate over an empty window would be a number about nothing.
Measured directly from 1 video with a duration reading, out of the posts we hold for this channel — not this channel’s whole posting history, only the sample this register has actually read. An exact reading to the second, taken from the post itself rather than from Telegram’s own rounded chrome, so it carries no ≈ mark.
Excellent news. We expect a new model on the Gonka network — deepseek-v4-flash. Fast and smart. It is preliminarily known that its presence on the network will be significant, and additional power will be added, which means there will be greater stability and uptime. Preliminarily waiting until the end of this week. 🤞
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 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.
Posted without readable text
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%.
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 …
Important: Kimi K2.6 will be disconnected for a few days today, but will most likely return to operation. Qwen will leave us completely. And soon we will raise the most relevant and desirable model GLM 5.2
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.
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. ❤️
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. 🏎🏎
Important: for correct operation, replace the base address with this https://hskyauefqcgbvgvxkluj.supabase.co/functions/v1/gonka Or go to the control panel, the new url is already placed there
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 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. Ev…
What is Gonka AI? How The REAL Decentralized AI Network Works
Showing the 12 most recent of 17 posts we hold for @GonkaAPI. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 8 October 2026 — this entry's latest reading, not the date you are reading this.
“Gonka-API.org” (@GonkaAPI), 320 subscribers as measured 8 October 2026. Telegram Register, tgregister.com/channel/GonkaAPI.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.