A
AkashML
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
93.3%2026-03-232026-04-21
Inference Latency
Meta: Llama 3.3 70B Instruct2384ms TTFT · 29 TPS
Google: Gemma 4 31B2703ms TTFT · 5 TPS
MiniMax: MiniMax M2.51859ms TTFT · 20 TPS
Qwen: Qwen3.5-35B-A3B551ms TTFT · 126 TPS
DeepSeek: DeepSeek V3.22778ms TTFT · 8 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Meta: Llama 3.3 70B Instruct | $0.13 | $0.40 | 2384ms | 29 |
| Google: Gemma 4 31B | $0.14 | $0.40 | 2703ms | 5 |
| MiniMax: MiniMax M2.5 | $0.20 | $1.18 | 1859ms | 20 |
| Qwen: Qwen3.5-35B-A3B | $0.23 | $1.80 | 551ms | 126 |
| DeepSeek: DeepSeek V3.2 | $0.28 | $0.42 | 2778ms | 8 |
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.