modelstatus.dev

Grok 4.3

x-ai/grok-4.3InputOutput

Compare its 4 providers Incident RSSCompare with Grok 4.20, Grok 4.20 Multi-Agent, Grok 4.5

CompareGrok 4.3

	State
xAIxai	Healthy	100%	99.87%	99.78%	99.53%	1.45s	8.18s	75 tps	1.0M	$1.25 / $2.50
xAIxai/zdr	Healthy	100%	99.90%	99.85%	99.51%	1.28s	3.09s	74 tps	1.0M	$1.25 / $2.50
xAIxai/priority	No data	—	99.59%	97.98%	96.42%	789ms	2.72s	71 tps	1.0M	$2.50 / $5.00
xAIxai/zdr/priority	No data	—	99.91%	98.48%	96.44%	605ms	2.41s	70 tps	1.0M	$2.50 / $5.00

xAI100%
Healthy24h 99.87%
7d
99.78%
30d
99.53%
p50
1.45s
p99
8.18s
Throughput
75 tps
Context
1.0M
$/Mtok
$1.25 / $2.50
xai
xAI100%
Healthy24h 99.90%
7d
99.85%
30d
99.51%
p50
1.28s
p99
3.09s
Throughput
74 tps
Context
1.0M
$/Mtok
$1.25 / $2.50
xai/zdr
xAI—
No data24h 99.59%
7d
97.98%
30d
96.42%
p50
789ms
p99
2.72s
Throughput
71 tps
Context
1.0M
$/Mtok
$2.50 / $5.00
xai/priority
xAI—
No data24h 99.91%
7d
98.48%
30d
96.44%
p50
605ms
p99
2.41s
Throughput
70 tps
Context
1.0M
$/Mtok
$2.50 / $5.00
xai/zdr/priority

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.

Throughput

Median tokens per second.

Daily availability

One row per endpoint · one dot per day · last 90 days.

Jul

Aug

Sep

Oct

xai/zdr/priority

worst hour ≥ 95%90–95%< 90%no data

Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 48 days with data, 18 endpoint-days below 90%.