Live Mistral status, checked every five minutes, and a log of recent Mistral outages. All times are UTC.
History logged by OutageRadar since Nov 8, 2026.
Get Mistral outage alerts in Discord or Slack, free.
Follow Mistral incidents in a feed reader: RSS feed.
For incidents before that, and for Mistral’s own explanations, see the official Mistral status page.
These AI APIs work with the official OpenAI library. Change the address and the key, pick a model from that provider’s list, and you’re running again. Each shows its live status, so you don’t switch to one that’s also down.
One key for many companies' models. Pick a model from a different company than the one that is down.
OpenRouter’s current model list · setup guide
Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=os.environ["OPENROUTER_API_KEY"],
)
reply = client.chat.completions.create(
model="PICK_FROM_LIST", # see OpenRouter's current model list
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "PICK_FROM_LIST", // see OpenRouter's current model list
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);Groq’s current model list · setup guide
Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.groq.com/openai/v1",
api_key=os.environ["GROQ_API_KEY"],
)
reply = client.chat.completions.create(
model="PICK_FROM_LIST", # see Groq's current model list
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.groq.com/openai/v1",
apiKey: process.env.GROQ_API_KEY,
});
const reply = await client.chat.completions.create({
model: "PICK_FROM_LIST", // see Groq's current model list
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);Google's OpenAI-compatible mode for the Gemini API.
Gemini’s current model list · setup guide
Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
api_key=os.environ["GEMINI_API_KEY"],
)
reply = client.chat.completions.create(
model="PICK_FROM_LIST", # see Gemini's current model list
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/",
apiKey: process.env.GEMINI_API_KEY,
});
const reply = await client.chat.completions.create({
model: "PICK_FROM_LIST", // see Gemini's current model list
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);OpenAI’s current model list · setup guide
Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openai.com/v1",
api_key=os.environ["OPENAI_API_KEY"],
)
reply = client.chat.completions.create(
model="PICK_FROM_LIST", # see OpenAI's current model list
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openai.com/v1",
apiKey: process.env.OPENAI_API_KEY,
});
const reply = await client.chat.completions.create({
model: "PICK_FROM_LIST", // see OpenAI's current model list
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);Test a backup in development before routing production traffic. Pick a model from a different company than the one that’s down. Your code talks to the provider directly; OutageRadar never sees your key. For a full automatic fallback setup, see TokenMargin.
Official status is what Mistral publishes on its own status page, read every five minutes.
Our check is OutageRadar asking Mistral’s API server for a reply at the same time. A reply, even “needs a key”, proves the server is up; it does not prove the AI is answering questions. The time shown is how long the API server took to answer our check, from Cloudflare’s network; it varies by moment and location and is not the speed of AI replies.
An incident is logged when the official status shows degraded performance or an outage, or when our check fails twice in a row. It ends after two healthy checks in a row. Times are when our checker saw the change, within five minutes.