G
Groq
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
96.7%2026-09-192026-10-18
Inference Latency
Meta: Llama 3.1 8B Instruct120ms TTFT · 324 TPS
OpenAI: gpt-oss-safeguard-20b143ms TTFT · 583 TPS
OpenAI: gpt-oss-20b326ms TTFT · 409 TPS
OpenAI: gpt-oss-120b168ms TTFT · 341 TPS
OpenAI: gpt-oss-120b (exacto)183ms TTFT · 439 TPS
Meta: Llama 3.3 70B Instruct467ms TTFT · 202 TPS
MiniMax: MiniMax M2.7521ms TTFT · 255 TPS
MoonshotAI: Kimi K2 0905 (exacto)114ms TTFT · 192 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| Meta: Llama 3.1 8B Instruct | $0.05 | $0.08 | 120ms | 324 |
| OpenAI: gpt-oss-safeguard-20b | $0.08 | $0.30 | 143ms | 583 |
| OpenAI: gpt-oss-20b | $0.08 | $0.30 | 326ms | 409 |
| OpenAI: gpt-oss-120b | $0.15 | $0.60 | 168ms | 341 |
| OpenAI: gpt-oss-120b (exacto) | $0.15 | $0.60 | 183ms | 439 |
| Meta: Llama 3.3 70B Instruct | $0.59 | $0.79 | 467ms | 202 |
| MiniMax: MiniMax M2.7 | $0.60 | $1.80 | 521ms | 255 |
| MoonshotAI: Kimi K2 0905 (exacto) | $1.00 | $3.00 | 114ms | 192 |
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.