Anthropic
LLMFREE TIERClaude — safety-first reasoning and long context
Degraded
Elevated response times or partial issues
Last checked 10/06/2026, 11:36:05 pm
882ms response
Uptime History91.33% uptime
2026-06-04Today
Uptime
91.33%
Avg Latency
896ms
P95 Latency
1142ms
Fastest
495ms
Checks
150
Response Time
Last 60 checks495ms min896ms avg7000ms max
💰 Pricing
claude-sonnet-4-5
Input: $3/1MOutput: $15/1M
claude-haiku-3-5: $0.80/$4.00
⚡ Rate Limits
free
RPM: 5TPM: 25,000Concurrent: 5
tier1
RPM: 50TPM: 50,000Concurrent: 5
After $5 spend.
tier4
RPM: 4,000TPM: 400,000
After $1000 spend.
🤖 Models (3)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Claude Sonnet 4.5 | llm | 200k | ✅ | ✅ | ✅ |
| Claude Opus 4.5 Most capable Anthropic model. $15/$75 per 1M | llm | 200k | ✅ | ✅ | ✅ |
| Claude Haiku 3.5 Fastest/cheapest Claude | llm | 200k | ✅ | ✅ | ✅ |
Recent Checks
Showing last 15Degraded
882ms10 June, 11:36 pm
Operational
860ms10 June, 10:17 pm
Operational
917ms10 June, 09:01 pm
Operational
853ms10 June, 07:37 pm
Operational
973ms10 June, 06:17 pm
Operational
962ms10 June, 04:50 pm
Operational
899ms10 June, 03:19 pm
Operational
795ms10 June, 01:46 pm
Operational
847ms10 June, 12:22 pm
Operational
856ms10 June, 11:20 am
Operational
940ms10 June, 10:04 am
Operational
824ms10 June, 09:31 am
Operational
861ms10 June, 08:52 am
Operational
786ms10 June, 08:13 am
Degraded
1015ms10 June, 07:36 am
Other LLM Providers
OpenAI
GPT-4o, o3, o1 — the benchmark everyone chases
DeepSeek
DeepSeek V3, R1 — elite reasoning at fraction of cost
Mistral AI
Mistral Large, Codestral — European frontier models
xAI Grok
Grok-3 — real-time web access, strong reasoning
AWS Bedrock
Managed foundation models — Claude, Llama, Titan on AWS
Azure OpenAI
OpenAI models on Microsoft Azure — enterprise SLA