What this Gemini API error means, whether it is on Google’s side or yours, and what to do now. All times are UTC.
Server-side: Google’s capacity
This error comes from Google’s servers, not from your code. Google publishes no machine-readable status feed, so the live signal below is our own check of its API server. Google’s own status page may not show it yet either.
No public status feed from the provider. Reachability checked by OutageRadar.
Our check: checking…
Google’s docs describe a 503 UNAVAILABLE as the service being temporarily overloaded or down, because it is temporarily running out of capacity.
It is a server-side error: your API key and request are not the cause.
Shape of the error body, from Google’s docs (the message text varies):
{
"error": {
"code": 503,
"message": "...",
"status": "UNAVAILABLE",
"details": [
"..."
]
}
}
You may not need this: the official SDKs retry on their own (see above). If you call the API directly, this helper waits and retries, using the server’s requested delay when you pass one. Google’s rule: retry 429, 408 and 5xx errors; never retry 400, 402 or 403.
Python
import random
import time
def with_retries(call, is_retryable, retry_after=lambda err: None, attempts=5):
"""Run call(). On a retryable error, wait and try again, up to attempts tries.
retry_after(err) returns the server's requested wait in seconds, or None."""
for attempt in range(attempts):
try:
return call()
except Exception as err:
if attempt == attempts - 1 or not is_retryable(err):
raise
wait = retry_after(err)
if wait is None:
wait = min(60, 2 ** attempt) + random.random() # backoff + jitter
time.sleep(wait)
JavaScript
async function withRetries(call, isRetryable, retryAfter = () => null, attempts = 5) {
// retryAfter(err) returns the server's requested wait in seconds, or null.
for (let attempt = 0; ; attempt++) {
try {
return await call();
} catch (err) {
if (attempt >= attempts - 1 || !isRetryable(err)) throw err;
let wait = retryAfter(err);
if (wait == null) wait = Math.min(60, 2 ** attempt) + Math.random(); // backoff + jitter
await new Promise((resolve) => setTimeout(resolve, wait * 1000));
}
}
}
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);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);Anthropic describes its OpenAI-compatible mode as mainly for testing; for long-term production use, its own SDK is recommended.
Claude’s current model list · setup guide
Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.anthropic.com/v1/",
api_key=os.environ["ANTHROPIC_API_KEY"],
)
reply = client.chat.completions.create(
model="PICK_FROM_LIST", # see Claude'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.anthropic.com/v1/",
apiKey: process.env.ANTHROPIC_API_KEY,
});
const reply = await client.chat.completions.create({
model: "PICK_FROM_LIST", // see Claude'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.
History logged by OutageRadar.
Full history: Is Gemini down?
Source: Gemini API errors (Google docs) · Gemini API troubleshooting: retry strategy (Google docs). Last checked against official docs: Nov 10, 2026. If the docs change, they win.