Mistral AI
LLMFREE TIERMistral Large, Codestral — European frontier models
Operational
All systems responding normally
Last checked 04/08/2026, 11:36:23 am
300ms response
Uptime History100.00% uptime
2026-07-30Today
Uptime
100.00%
Avg Latency
285ms
P95 Latency
341ms
Fastest
163ms
Checks
150
Response Time
Last 60 checks163ms min285ms avg760ms max
💰 Pricing
mistral-large-2
Input: $2/1MOutput: $6/1M
mistral-small: $0.10/$0.30
⚡ Rate Limits
free
RPM: 1TPM: 500,000
Experimental access only. Very strict.
premier
RPM: 60
Paid plan. Higher limits on request.
🤖 Models (3)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Mistral Large 2 | llm | 131k | — | ✅ | ✅ |
| Codestral Code specialist. Best context for code tasks | code | 256k | — | ✅ | ✅ |
| Mistral Small $0.10/$0.30 per 1M | llm | 33k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
300ms4 Aug, 11:36 am
Operational
292ms4 Aug, 10:52 am
Operational
263ms4 Aug, 10:03 am
Operational
252ms4 Aug, 09:35 am
Operational
278ms4 Aug, 09:07 am
Operational
300ms4 Aug, 08:40 am
Operational
320ms4 Aug, 08:14 am
Operational
254ms4 Aug, 07:43 am
Operational
283ms4 Aug, 07:14 am
Operational
296ms4 Aug, 06:44 am
Operational
329ms4 Aug, 06:14 am
Operational
378ms4 Aug, 05:32 am
Operational
194ms4 Aug, 04:52 am
Operational
301ms4 Aug, 04:09 am
Operational
301ms4 Aug, 03:27 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
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