I
Ionstream
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-03-232026-04-21
Inference Latency
Google: Gemma 4 26B A4B 899ms TTFT · 6 TPS
Qwen: Qwen3 Coder Next380ms TTFT · 113 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Google: Gemma 4 26B A4B | $0.07 | $0.35 | 899ms | 6 |
| Qwen: Qwen3 Coder Next | $0.15 | $0.80 | 380ms | 113 |
Community Reviews
4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15
Reliable service, great API documentation.
mlresearcher
★★★★☆2025-06-10
Good performance but support could be faster.