Groq
groq.comInferenceprotocol: x402first seen 183d ago
Ultra-fast LLM inference (Llama, DeepSeek, Gemma)
Endpoints
4
Uptime · 24h
50.0%
22 / 44 probes
Avg latency · 24h
191 ms
p90 270 ms
Total calls
0
0 unique payers
Healthy probes · last 24h
6 hour buckets · hover for per-bucket stats
Endpoints
Ordered: active first, healthy first, cheapest first. Up to 200 shown.
| Endpoint | Method | Price | Network | Last status | Latency | Probed |
|---|---|---|---|---|---|---|
| https://blockrun.ai/v1/models | GET | — | eip155:8453 | 200 | 280 ms | 2m ago |
| https://blockrun.ai/v1/chat/completions | POST | — | eip155:8453 | 402 | 163 ms | 6m ago |
| https://api.venice.ai/api/v1/chat/completions | POST | 0.001000 USDC | eip155:8453 | 400 | 143 ms | 6m ago |
| https://api.venice.ai/api/v1/responses | POST | 0.001000 USDC | eip155:8453 | 400 | 175 ms | 6m ago |