Registered workers
1
Active gateway workers
Top Models
All time
Non-streamed
gpt-4o
28.6%
gpt-5-nano
21.4%
jrnlr
21.4%
lod/auto
14.3%
lod-paperclip
7.1%
qwen3.5-35b-a3b
7.1%
Streamed
lod/auto
85.7%
lod-paperclip
8.0%
qwen/qwen3.5-35b-a3b
5.6%
deepseek-ai/DeepSeek-V3.1
0.7%
openai/gpt-5-nano
0.1%
Last 24
Non-streamed
No model usage data yet.
Streamed
No model usage data yet.
Failover Rate
All time
Non-streamed
1st attempt
100.0%
Streamed
1st attempt
100.0%
Last 24
Non-streamed
No failover success data yet.
Streamed
No failover success data yet.
Average Tokens / Second by Model
All time
Non-streamed
| Model | Avg tokens/sec |
|---|---|
| qwen3.5-35b-a3b | 148.65 |
| jrnlr | 122.90 |
| gpt-4o | 104.10 |
| gpt-5-nano | 72.48 |
| lod/auto | 17.50 |
| lod-paperclip | 1.79 |
Streamed
| Model | Avg tokens/sec |
|---|---|
| lod-paperclip | 67.22 |
Last 24
Non-streamed
No token throughput data yet.
Streamed
No token throughput data yet.
Failed Requests
All time
Non-streamed
Failed request rate
56.25%
18 of 32 requests
Streamed
Failed request rate
4.59%
477 of 10381 requests
Last 24
Non-streamed
No request data yet.
Streamed
No request data yet.