C
Cloudflare
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-03-232026-04-21
Inference Latency
IBM: Granite 4.0 Micro453ms TTFT · 16 TPS
Meta: Llama 3.2 1B Instruct252ms TTFT · 68 TPS
Meta: Llama 3.2 3B Instruct293ms TTFT · 75 TPS
Mistral: Mistral 7B Instruct v0.1521ms TTFT · 9 TPS
Meta: Llama 3.1 8B Instruct446ms TTFT · 15 TPS
Meta: Llama 3.3 70B Instruct399ms TTFT · 21 TPS
Google: Gemma 3 12B384ms TTFT · 49 TPS
Mistral: Mistral Small 3.1 24B490ms TTFT · 24 TPS
MoonshotAI: Kimi K2.51271ms TTFT · 46 TPS
MoonshotAI: Kimi K2.68111ms TTFT · 37 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| IBM: Granite 4.0 Micro | $0.02 | $0.11 | 453ms | 16 |
| Meta: Llama 3.2 1B Instruct | $0.03 | $0.20 | 252ms | 68 |
| Meta: Llama 3.2 3B Instruct | $0.05 | $0.34 | 293ms | 75 |
| Mistral: Mistral 7B Instruct v0.1 | $0.11 | $0.19 | 521ms | 9 |
| Meta: Llama 3.1 8B Instruct | $0.15 | $0.29 | 446ms | 15 |
| Meta: Llama 3 8B Instruct | $0.28 | $0.83 | — | — |
| Meta: Llama 3.3 70B Instruct | $0.29 | $2.25 | 399ms | 21 |
| Google: Gemma 3 12B | $0.35 | $0.56 | 384ms | 49 |
| Mistral: Mistral Small 3.1 24B | $0.35 | $0.56 | 490ms | 24 |
| Llama Guard 3 8B | $0.48 | $0.03 | — | — |
| MoonshotAI: Kimi K2.5 | $0.60 | $3.00 | 1271ms | 46 |
| Qwen2.5 Coder 32B Instruct | $0.66 | $1.00 | — | — |
| MoonshotAI: Kimi K2.6 | $0.95 | $4.00 | 8111ms | 37 |
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.