Is Mistral AI down?
No, Mistral AI is not down.
Mistral AI’s status page reports no incidents, api.mistral.ai and chat.mistral.ai responded from 6 regions, and nobody reported problems in the last hour.
- Official statusNo incidentsstatus.mistral.ai
- Reachable6 of 6 regionsMistral API 6/6 · chat.mistral.ai edge 6/6
- Reports in the last hour0Normal
Mistral AI’s status page
From status.mistral.ai. Read at
- Completion APIOperational
- Embedding APIOperational
- OCR APIOperational
- Agents APIOperational
- Conversations APIOperational
- Fine-Tuning APIOperational
- Audio APIOperational
- Integrations APIOperational
Show all 16 components
- Files APIOperational
- Batch APIOperational
- Workflows APIOperational
- ConsoleOperational
- Prompts APIOperational
- Responses APIOperational
- Skills APIOperational
- VibeOperational
Not working for me
Pick what’s broken. Your report shows up on the chart below within a few minutes.
Last 24 hours
No problems in the last 24 hours, median response 363 ms, and 1 report.
- Operational
- Degraded
- Partial outage
- Major outage
- No data
- Reachability check (api.mistral.ai)
By region
| Region | Mistral API api.mistral.ai | chat.mistral.ai edge chat.mistral.ai |
|---|---|---|
| N. Virginia | Up · 169 ms | Up · 260 ms |
| Oregon | Up · 202 ms | Up · 630 ms |
| Frankfurt | Up · 68 ms | Up · 31 ms |
| Singapore | Up · 312 ms | Up · 503 ms |
| Tokyo | Up · 305 ms | Up · 709 ms |
| São Paulo | Up · 201 ms | Up · 546 ms |
Each row shows the latest result from that region. How we check
Last 90 days
We have checked Mistral AI ourselves since Oct 28, 2026. Earlier days come from its status page.
18 days with problems in the last 90 days.
Recent incidents
Incidents: 10 in the last 30 days and 24 in the last 90, lasting a median of 36 min.
- Mistral AI disruptionDegraded48 min
- Vibe Code Web and Vibe Work sessions may fail to start or resumeDegraded2 days
- Vibe Code Web and Vibe Work sessions may fail to start or resumeDegraded4 h 49 min
- Mistral Small 4 Availability DegradationDegraded2 h 49 min
- Vibe Code Web sessions failingDegraded36 min
- Vibe is experiencing high latency with GLM 5.3Degraded1 h 11 min
- Some Vibe Code Web sessions are terminating unexpectedly or are unable to startPartial outage25 min
- Fixed errors on workflow APIsDegraded26 min
- Total Unavailability on ML4 GLM5.2 and GLM5.3Partial outage34 min
- Some Vibe Code Web sessions are terminating unexpectedlyDegraded2 h 54 min
If Mistral AI isn’t working for you
Mistral AI is a French AI company offering the Le Chat assistant and an API for its open and commercial models.
Common Mistral AI errors
| Error | What it means | Usually | What to do |
|---|---|---|---|
401 Unauthorized | The API key is missing, invalid, expired or from a different workspace. | Your side | Check the key and send it as Authorization: Bearer YOUR_API_KEY. Source |
402 Payment Required | A billing condition blocks the request, such as zero prepaid credits or a reached spending limit. | Your side | Add credits, update the payment method or raise the spending limit. Source |
429 Too Many Requests | You exceeded your tier's requests per second, tokens per minute or concurrent request limit. | Your side | Back off exponentially, check the Retry-After header, or use batch processing for bulk jobs. Source |
503 Service Unavailable | The service is temporarily overloaded or under maintenance. | Heavy load | Retry with exponential backoff and check status.mistral.ai. Source |
500 Internal Server Error | An unexpected error occurred on Mistral's side. | An outage | Retry after a short delay; if it persists, check status.mistral.ai. Source |
Is it just you?
- Compare Le Chat in the browser with a direct API call: they can fail separately.
- Check the Limits page in the Mistral console to see whether you are near your requests-per-second or token quota.
- Try a smaller or different model; a 429 or 503 on one model while others work points to capacity on that model.
- Check status.mistral.ai for incidents before changing your code.
Alternatives to Mistral AI
Questions
You exceeded a limit for your subscription tier: requests per second, tokens per minute or concurrent requests. Limits are set per organization; wait, back off and check the Limits page in the console.
Mistral posts incidents at status.mistral.ai. This page shows that status next to our own reachability checks from several regions and real test requests to the API.
Sources: docs.mistral.ai, status.mistral.ai
Get alerted when Mistral AI breaks your app.
If your product depends on Mistral AI, your users feel its outages too. Point a Site Qwality monitor at the Mistral AI endpoint you use and at your own site, and we alert you on Slack, email, SMS or a webhook as soon as either one stops answering.