modelstatus.dev

← Mixtral 8x22B Instruct

Mixtral 8x22B Instruct: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

Current state

	State
Mistralmistral	No data	—	100%	100%◆ (best)	100%	339ms	1.24s	150 tps◆ (best)	66K	$2.00 / $6.00◆ (best)
Mistralmistral/eu	No data	—	100%	100%◆ (best)	100%◆ (best)	—	—	—	66K	$2.20 / $6.60
Mistralmistral/zdr	No data	—	100%	100%	99.98%	326ms◆ (best)	720ms◆ (best)	144 tps	66K	$2.00 / $6.00◆ (best)

Mistral—
No data24h 100%
7d
100%◆ (best)
30d
100%
p50
339ms
p99
1.24s
Throughput
150 tps◆ (best)
Context
66K
$/Mtok
$2.00 / $6.00◆ (best)
mistral
Mistral—
No data24h 100%
7d
100%◆ (best)
30d
100%◆ (best)
p50
—
p99
—
Throughput
—
Context
66K
$/Mtok
$2.20 / $6.60
mistral/eu
Mistral—
No data24h 100%
7d
100%
30d
99.98%
p50
326ms◆ (best)
p99
720ms◆ (best)
Throughput
144 tps
Context
66K
$/Mtok
$2.00 / $6.00◆ (best)
mistral/zdr

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

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.

Throughput

Median tokens per second.