mistral — AI API latency & reliability by region

Last verified September 07, 2026

As of September 07, 2026, the mistral AI API responds in 100 ms p50 (edge, time-to-first-byte) from Europe (Germany) — its fastest measured region — with 100% uptime. Slowest is Asia (Tokyo) at 323 ms p50.

Is mistral down right now?

Was mistral down in the last 3 days?

No. All 3,456 probes from 4 region(s) reached the mistral API in the last 72 hours.

What Mistral’s own status page reported

Mistral publishes no machine-readable status page, so there is nothing to set against the measurements above.

Is mistral getting faster or slower?

hourly p50 latencyall probes succeededsome probes failedhalf or more failedno data

One panel per region: the line is the hourly p50 edge latency (shared scale, ms), the strip beneath it is the outcome of that hour’s host probes. Hover any hour for the numbers. Flat is good; a rising line means the endpoint is slowing down from that origin, a gap means no probe succeeded in that hour.

How fast is the mistral API from each region?

Measured from Europe (Germany), mistral responds in 100 ms; from Asia (Tokyo) the same API takes 323 ms — 3.2× longer for an identical request. That difference is the network path, not the model, and it applies to every call you make.

What is actually being measured here?

A probe in each region opens a real connection to mistral’s own API host every five minutes and times DNS resolution, the TCP handshake, the TLS handshake and the first byte of the response. Nothing is routed through a gateway or aggregator, so these figures describe mistral’s infrastructure rather than a reseller’s. Uptime counts a probe as failed only when the service genuinely fails — a 401 from an unauthenticated probe means the endpoint answered correctly and is counted as up.

What this page does not tell you

These are edge latency numbers: the time before the model begins generating. They say nothing about answer quality, throughput, price, or how long a full completion takes — those depend on the model you call. Edge latency matters because it is unavoidable: it is paid on every request, before a single token exists, and no prompt engineering removes it. Where an API key is available, inference time-to-first-token is measured separately and shown on the region pages with the model named next to the figure. Likewise, an unauthenticated probe cannot see errors that hit only some models or some accounts — the kind a status page usually reports — which is why Mistral’s own reports are shown next to the measurements rather than folded into them.

How does mistral compare to other providers?

• mistral vs openai latency
• mistral vs anthropic latency
• mistral vs google latency
• mistral vs deepseek latency
• mistral vs xai latency
• mistral vs groq latency
• mistral vs cerebras latency
• mistral vs sambanova latency
• mistral vs together latency
• mistral vs fireworks latency
• mistral vs openrouter latency