modelstatus.dev

Saba: 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)	99.97%	—	—	—	33K	$0.200 / $0.600◆ (best)
Mistralmistral/eu	No data	—	—	100%◆ (best)	100%◆ (best)	404ms	662ms◆ (best)	138 tps◆ (best)	33K	$0.220 / $0.660
Mistralmistral/zdr	No data	—	100%	100%◆ (best)	99.97%	384ms◆ (best)	950ms	138 tps	33K	$0.200 / $0.600◆ (best)

Mistral—
No data24h 100%
7d
100%◆ (best)
30d
99.97%
p50
—
p99
—
Throughput
—
Context
33K
$/Mtok
$0.200 / $0.600◆ (best)
mistral
Mistral—
No data24h —
7d
100%◆ (best)
30d
100%◆ (best)
p50
404ms
p99
662ms◆ (best)
Throughput
138 tps◆ (best)
Context
33K
$/Mtok
$0.220 / $0.660
mistral/eu
Mistral—
No data24h 100%
7d
100%◆ (best)
30d
99.97%
p50
384ms◆ (best)
p99
950ms
Throughput
138 tps
Context
33K
$/Mtok
$0.200 / $0.600◆ (best)
mistral/zdr

Measured 4m 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.