Gonka Network
Network Status
Real-time model availability and latency. Automatically updated every minute.
Overall
All systems operational
MiniMax M2.7
by MiniMax
- Uptime 24h
- 99.3%
- Uptime 7d
- 99.2%
- Median latency
- 313 ms
- 95th percentile latency
- 4.33 с
- Checks in 15 min
- 15 / 15
- Last check
- 48 seconds ago
- Input Context
- 195K
- Max Output
- 8K
- VRAM
- 320 GB
Hourly availability for the last 24 h
Kimi K2.6
by Moonshot AI
- Uptime 24h
- 99.7%
- Uptime 7d
- 99.1%
- Median latency
- 245 ms
- 95th percentile latency
- 607 ms
- Checks in 15 min
- 15 / 15
- Last check
- 48 seconds ago
- Input Context
- 195K
- Max Output
- 8K
- VRAM
- 720 GB
Hourly availability for the last 24 h
DeepSeek V4 Flash
by DeepSeek
- Uptime 24h
- 99.8%
- Uptime 7d
- 98.7%
- Median latency
- 267 ms
- 95th percentile latency
- 593 ms
- Checks in 15 min
- 15 / 15
- Last check
- 48 seconds ago
- Input Context
- 371K
- Max Output
- 32K
- VRAM
- 280 GB
Hourly availability for the last 24 h
Incidents in the last 48 hours
- 2 min
Degraded
MiniMax M2.7
8/18/2026, 1:36:19 AM → 8/18/2026, 1:38:18 AM
- 7 min
Degraded
MiniMax M2.7
8/18/2026, 1:28:48 AM → 8/18/2026, 1:35:18 AM
- 1 min
Degraded
DeepSeek V4 Flash
8/17/2026, 9:26:18 PM → 8/17/2026, 9:27:18 PM
- 1 min
Degraded
DeepSeek V4 Flash
8/17/2026, 9:24:19 PM → 8/17/2026, 9:25:18 PM
- 2 min
Degraded
MiniMax M2.7
8/17/2026, 9:24:19 PM → 8/17/2026, 9:26:18 PM
- 4 min
Degraded
Kimi K2.6
8/17/2026, 9:23:18 PM → 8/17/2026, 9:27:18 PM
- 1 min
Degraded
DeepSeek V4 Flash
8/17/2026, 9:22:18 PM → 8/17/2026, 9:23:18 PM
- 3 min
Degraded
MiniMax M2.7
8/17/2026, 9:18:26 PM → 8/17/2026, 9:21:18 PM
- 3 min
Degraded
DeepSeek V4 Flash
8/17/2026, 9:18:26 PM → 8/17/2026, 9:21:18 PM
- 1 min
Degraded
DeepSeek V4 Flash
8/17/2026, 9:16:48 PM → 8/17/2026, 9:17:18 PM
- 5 min
Degraded
Kimi K2.6
8/17/2026, 9:16:48 PM → 8/17/2026, 9:21:18 PM
- 1 min
Degraded
MiniMax M2.7
8/17/2026, 9:16:48 PM → 8/17/2026, 9:17:18 PM
Models under monitoring
MiniMax M2.7
by MiniMax. Available via the unified OpenAI- and Anthropic-compatible JoinGonka API. Current status and uptime can be found in the cards above.
Kimi K2.6
by Moonshot AI. Available via the unified OpenAI- and Anthropic-compatible JoinGonka API. Current status and uptime can be found in the cards above.
DeepSeek V4 Flash
by DeepSeek. Available via the unified OpenAI- and Anthropic-compatible JoinGonka API. Current status and uptime can be found in the cards above.
Frequently asked questions
- What does 'Quality degradation' mean?
- Some test requests failed or had a noticeable delay. The service is still working, but users may see timeouts or slowdowns. This is usually a temporary peak load on the network.
- What does 'Failure' mean?
- More than half of the requests do not receive a response within 15 seconds. The model is effectively unavailable. We open an incident and continue checks — the status is automatically restored as soon as the network responds.
- Where does the data come from?
- Our backend makes a signed inference request directly to Gonka network nodes once a minute via the gonka-openai SDK. We do not depend on third-party monitors — exactly the same nodes as for user requests.
- How often is the page updated?
- The widget automatically reloads data every minute. To keep the data fresh in real time, you can simply leave the tab open.
How we measure
Once a minute, we send a test request to each Gonka network model and record the response and latency. Status is determined based on the last 15 minutes: "Outage" - if more than half of the probes failed; "Degraded performance" - if more than 20% failed, or if the response latency is more than 2.5 times the typical level.