Model latency
Time to first token and output throughput from the last 24 hours, grouped by Freebuff model.
Updated 9 min ago
Median TTFT
4.5s
7.8M samples in 24h
P95 TTFT
19s
Slower tail across all models
Output speed
70 tok/s
Output tokens per second after TTFT
Lowest Median
1.6s
Solar Mini 4 · 4,944 samples
Models
9
Reporting TTFT samples
By model
Sorted by median TTFT. Bars show P95 latency.
Last 24 hours
Solar Mini 4
Median
1.6s
P95
4.0s
Tok/s
114
4,944 sampleshourly median
DeepSeek V4.1 Flash
Median
1.7s
P95
20s
Tok/s
134
2.6M sampleshourly median
Space Bunny Alpha
Median
1.7s
P95
3.1s
Tok/s
141
23K sampleshourly median
Gemini 3.8 Flash
Median
2.1s
P95
7.0s
Tok/s
504
20K sampleshourly median
MiMo 2.6 Flash
Median
4.4s
P95
17s
Tok/s
63
252K sampleshourly median
MiMo 2.6 Pro
Median
4.4s
P95
22s
Tok/s
48
37K sampleshourly median
Muse Spark 1.2
Median
4.6s
P95
39s
Tok/s
1,079
19K sampleshourly median
GLM 5.3 Flash
Median
5.5s
P95
18s
Tok/s
52
4.7M sampleshourly median
GPT-6 Luna
Median
6.2s
P95
16s
Tok/s
100
146K sampleshourly median