System status
Live availability and latency for every text model on BigModel.io.
Doubao
- Doubao Seed 2.1 Pro
doubao-seed-2.1-pro- 30 days
- 93.91%
- Latency
- 2.93 s
- Doubao Seed Evolving
doubao-seed-evolving- 30 days
- —
- Latency
- —
- Doubao Seed 2.1 Lite
doubao-seed-2.1-lite- 30 days
- —
- Latency
- —
- Doubao Seed 2.0 Mini
doubao-seed-2.0-mini- 30 days
- —
- Latency
- —
Kimi
- Kimi K3
kimi-k3- 30 days
- 88.12%
- Latency
- 3.80 s
- Kimi K2.8 Preview
kimi-k2.8-preview- 30 days
- —
- Latency
- —
DeepSeek
- DeepSeek V4 Pro
deepseek-v4-pro- 30 days
- 68.98%
- Latency
- 2.20 s
- DeepSeek V4 Flash
deepseek-v4-flash- 30 days
- 94.20%
- Latency
- 1.97 s
- DeepSeek V4.1 Flash
deepseek-v4.1-flash- 30 days
- —
- Latency
- —
MiniMax
- MiniMax M3
minimax-m3- 30 days
- 93.62%
- Latency
- 1.96 s
How we measure
We check each model regularly and include real requests made through BigModel.io. Availability is the share of those that succeeded; latency is the typical time to a complete response.
Latency figures are typical values, not a guarantee. A model shows "Monitoring" until it has enough recent data.
Something not working for you? support@bigmodel.io · All models