Model latency
Time to first token and output throughput from the last 24 hours, grouped by Freebuff model.
Updated 13 min ago
Median TTFT
1.9s
5M samples in 24h
P95 TTFT
6.0s
Slower tail across all models
Output speed
132 tok/s
Output tokens per second after TTFT, stalls and bursts left out
Lowest Median
1.6s
GLM 5.3 Flash ยท 120 samples
Models
10
Reporting TTFT samples
By model
Sorted by median TTFT. Bars show P95 latency.
Last 24 hours
GLM 5.3 Flash
Median
1.6s
P95
2.8s
Tok/s
81
120 sampleshourly median
DeepSeek V4.1 Flash 10/17
Median
1.6s
P95
4.5s
Tok/s
133
3.7M sampleshourly median
DeepSeek V4.1 Flash Fast 10/17
Median
1.7s
P95
4.6s
Tok/s
134
330K sampleshourly median
Muse Spark 1.3
Median
3.0s
P95
6.6s
Tok/s
177
140K sampleshourly median
Solar Mini 4
Median
3.0s
P95
6.2s
Tok/s
108
330K sampleshourly median
Solar Pro 4
Median
3.5s
P95
15s
Tok/s
73
450K sampleshourly median
GPT-6.1 Sol
Median
3.8s
P95
11s
Tok/s
70
63 sampleshourly median
GPT-6.1 Terra
Median
4.0s
P95
11s
Tok/s
213
16K sampleshourly median
GPT-6 Luna
Median
5.4s
P95
20s
Tok/s
298
61K sampleshourly median
Gemini 3.8 Flash
Median
13s
P95
17s
Tok/s
150
4 sampleshourly median