Operational
All systems responding normally
Last checked 21/09/2026, 9:43:17 am
673ms response
Uptime History100.00% uptime
2026-09-19Today
Uptime
100.00%
Avg Latency
772ms
P95 Latency
1020ms
Fastest
400ms
Checks
150
Response Time
Last 60 checks400ms min772ms avg1618ms max
💰 Pricing
grok-3
Input: $3/1MOutput: $15/1M
grok-3-mini: $0.30/$0.50
⚡ Rate Limits
standard
RPM: 50
Standard API tier. Enterprise: custom limits.
🤖 Models (2)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Grok 3 Real-time web access. Strong reasoning | llm | 131k | — | ✅ | ✅ |
| Grok 3 Mini $0.30/$0.50 per 1M. Fast and cheap | llm | 131k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
673ms21 Sept, 09:43 am
Operational
660ms21 Sept, 09:34 am
Operational
969ms21 Sept, 09:21 am
Operational
642ms21 Sept, 09:09 am
Operational
857ms21 Sept, 08:52 am
Operational
733ms21 Sept, 08:42 am
Operational
939ms21 Sept, 08:34 am
Operational
969ms21 Sept, 08:22 am
Operational
791ms21 Sept, 08:09 am
Operational
630ms21 Sept, 07:53 am
Operational
965ms21 Sept, 07:42 am
Operational
915ms21 Sept, 07:34 am
Operational
907ms21 Sept, 07:21 am
Operational
890ms21 Sept, 07:09 am
Operational
797ms21 Sept, 06:52 am
Other LLM Providers
OpenAI
GPT-4o, o3, o1 — the benchmark everyone chases
Anthropic
Claude — safety-first reasoning and long context
DeepSeek
DeepSeek V3, R1 — elite reasoning at fraction of cost
Mistral AI
Mistral Large, Codestral — European frontier models
AWS Bedrock
Managed foundation models — Claude, Llama, Titan on AWS
Azure OpenAI
OpenAI models on Microsoft Azure — enterprise SLA