Together AI status

Q: Is Together AI down right now?

Together AI does not publish a machine-readable status feed. This page shows the success rate LLM Gateway measured on real Together AI traffic over the last 24 hours and 90 days.

Q: How is Together AI uptime measured?

Uptime is the share of requests to Together AI through LLM Gateway that completed without a provider or gateway error. Invalid requests (4xx caused by the request) and traffic on customers' own provider keys are excluded.

Q: What happens to my requests when Together AI has an outage?

LLM Gateway retries failed requests on another healthy provider serving the same model and routes new traffic away from degraded providers. 10 of the 10 Together AI models on LLM Gateway can fail over this way.

Q: How often does this page update?

Every five minutes. Measured uptime comes from LLM Gateway's hourly traffic rollups; the official status and incidents come from the provider's status page.

Is Together AI down? Live official status, incidents, and the uptime LLM Gateway measured on real Together AI traffic.

No official feed

Measured uptime

Success rate of Together AI requests through LLM Gateway, by UTC day.

Last 24 hours

100%

68,017 requests

Last 90 days

99.87%

1,427,098 requests

Aug 11: Not enough traffic to measure
Aug 12: Not enough traffic to measure
Aug 13: Not enough traffic to measure
Aug 14: Not enough traffic to measure
Aug 15: Not enough traffic to measure
Aug 16: Not enough traffic to measure
Aug 17: Not enough traffic to measure
Aug 18: Not enough traffic to measure
Aug 19: Not enough traffic to measure
Aug 20: Not enough traffic to measure
Aug 21: Not enough traffic to measure
Aug 22: Not enough traffic to measure
Aug 23: Not enough traffic to measure
Aug 24: Not enough traffic to measure
Aug 25: Not enough traffic to measure
Aug 26: 99.16% uptime over 478 requests
Aug 27: 99.43% uptime over 3,177 requests
Aug 28: 99.94% uptime over 3,201 requests
Aug 29: 99.64% uptime over 3,893 requests
Aug 30: 99.09% uptime over 3,958 requests
Aug 31: 99.65% uptime over 12,609 requests
Sep 1: 98.70% uptime over 1,156 requests
Sep 2: 99.27% uptime over 1,226 requests
Sep 3: 97.59% uptime over 1,740 requests
Sep 4: 93.10% uptime over 4,736 requests
Sep 5: 98.68% uptime over 680 requests
Sep 6: 99.54% uptime over 217 requests
Sep 7: 99.10% uptime over 782 requests
Sep 8: 99.07% uptime over 2,040 requests
Sep 9: 99.23% uptime over 2,873 requests
Sep 10: 99.76% uptime over 2,072 requests
Sep 11: 99.08% uptime over 3,384 requests
Sep 12: 99.70% uptime over 1,663 requests
Sep 13: 99.45% uptime over 2,364 requests
Sep 14: 98.75% uptime over 4,233 requests
Sep 15: 99.55% uptime over 3,094 requests
Sep 16: 99.80% uptime over 9,048 requests
Sep 17: 99.45% uptime over 3,853 requests
Sep 18: 99.91% uptime over 5,657 requests
Sep 19: 100% uptime over 1,584 requests
Sep 20: 100% uptime over 878 requests
Sep 21: 99.00% uptime over 1,806 requests
Sep 22: 99.56% uptime over 7,252 requests
Sep 23: 99.81% uptime over 5,723 requests
Sep 24: 99.77% uptime over 3,079 requests
Sep 25: 99.88% uptime over 3,391 requests
Sep 26: 99.47% uptime over 1,311 requests
Sep 27: 99.90% uptime over 25,045 requests
Sep 28: 99.53% uptime over 27,157 requests
Sep 29: 99.71% uptime over 32,939 requests
Sep 30: 99.88% uptime over 14,423 requests
Oct 1: 99.70% uptime over 10,588 requests
Oct 2: 99.24% uptime over 8,464 requests
Oct 3: 99.87% uptime over 3,033 requests
Oct 4: 99.72% uptime over 1,445 requests
Oct 5: 99.90% uptime over 5,959 requests
Oct 6: 99.18% uptime over 6,617 requests
Oct 7: 99.59% uptime over 4,658 requests
Oct 8: 99.82% uptime over 6,560 requests
Oct 9: 99.87% uptime over 8,239 requests
Oct 10: 99.33% uptime over 2,236 requests
Oct 11: 99.79% uptime over 8,487 requests
Oct 12: 99.59% uptime over 19,459 requests
Oct 13: 99.90% uptime over 18,320 requests
Oct 14: 99.91% uptime over 32,636 requests
Oct 15: 99.80% uptime over 24,979 requests
Oct 16: 99.94% uptime over 9,841 requests
Oct 17: 100% uptime over 1,300 requests
Oct 18: 100% uptime over 856 requests
Oct 19: 99.96% uptime over 28,925 requests
Oct 20: 99.90% uptime over 27,942 requests
Oct 21: 99.89% uptime over 29,043 requests
Oct 22: 99.97% uptime over 57,582 requests
Oct 23: 99.98% uptime over 78,456 requests
Oct 24: 99.98% uptime over 55,924 requests
Oct 25: 99.98% uptime over 40,430 requests
Oct 26: 99.85% uptime over 44,261 requests
Oct 27: 99.95% uptime over 12,455 requests
Oct 28: 99.98% uptime over 17,377 requests
Oct 29: 99.93% uptime over 29,837 requests
Oct 30: 100% uptime over 79,629 requests
Oct 31: 99.96% uptime over 12,174 requests
Nov 1: 99.99% uptime over 11,767 requests
Nov 2: 99.98% uptime over 43,923 requests
Nov 3: 99.98% uptime over 80,059 requests
Nov 4: 99.99% uptime over 96,734 requests
Nov 5: 99.98% uptime over 118,167 requests
Nov 6: 99.97% uptime over 109,864 requests
Nov 7: 99.98% uptime over 11,052 requests
Nov 8: 100% uptime over 65,098 requests

30 days ago90 days agoToday

≥ 99.5%
≥ 98%
≥ 95%
≥ 90%
< 90%
No data
Official incident

Automatic failover

When Together AI fails or slows down, LLM Gateway retries the request on another healthy provider serving the same model, with no change to your code. 10 of 10 Together AI models can fail over.

Together AI models and pricing Official status page

Frequently asked questions

Is Together AI down right now?

Together AI does not publish a machine-readable status feed. This page shows the success rate LLM Gateway measured on real Together AI traffic over the last 24 hours and 90 days.

How is Together AI uptime measured?

Uptime is the share of requests to Together AI through LLM Gateway that completed without a provider or gateway error. Invalid requests (4xx caused by the request) and traffic on customers' own provider keys are excluded.

What happens to my requests when Together AI has an outage?

LLM Gateway retries failed requests on another healthy provider serving the same model and routes new traffic away from degraded providers. 10 of the 10 Together AI models on LLM Gateway can fail over this way.

How often does this page update?

Every five minutes. Measured uptime comes from LLM Gateway's hourly traffic rollups; the official status and incidents come from the provider's status page.