modelstatus.dev

← Mistral Medium 3

Mistral Medium 3: 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	—	99.97%	99.21%	98.85%	334ms◆ (best)	4.85s	130 tps	131K	$0.400 / $2.00◆ (best)
Mistralmistral/eu	No data	—	100%	100%◆ (best)	100%◆ (best)	—	—	—	131K	$0.440 / $2.20
Mistralmistral/zdr	No data	—	99.98%	99.79%	98.95%	342ms	4.74s◆ (best)	133 tps◆ (best)	131K	$0.400 / $2.00◆ (best)

Mistral—
No data24h 99.97%
7d
99.21%
30d
98.85%
p50
334ms◆ (best)
p99
4.85s
Throughput
130 tps
Context
131K
$/Mtok
$0.400 / $2.00◆ (best)
mistral
Mistral—
No data24h 100%
7d
100%◆ (best)
30d
100%◆ (best)
p50
—
p99
—
Throughput
—
Context
131K
$/Mtok
$0.440 / $2.20
mistral/eu
Mistral—
No data24h 99.98%
7d
99.79%
30d
98.95%
p50
342ms
p99
4.74s◆ (best)
Throughput
133 tps◆ (best)
Context
131K
$/Mtok
$0.400 / $2.00◆ (best)
mistral/zdr

Measured 5m 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, averaged over the hour.

Throughput

Median tokens per second.