modelstatus.dev

Mistral Small 3.2 24B

mistralai/mistral-small-3.2-24b-instruct

Compare with Mistral Nemo, Mistral Large, Saba

CompareMistral Small 3.2 24B

	State
Venicevenice/fp8fp8	Healthy	100%	98.43%	97.93%	97.93%	672ms	5.41s	17 tps	256K	$0.094 / $0.250
Parasailparasail/bf16bf16	Healthy	99.69%	99.23%	99.09%	99.09%	702ms	7.79s	25 tps	131K	$0.090 / $0.300
DeepInfradeepinfra/fp8fp8	No data	—	98.35%	96.95%	96.95%	408ms	2.99s	23 tps	128K	$0.075 / $0.200

Venice100%
Healthy24h 98.43%
7d
97.93%
30d
97.93%
p50
672ms
p99
5.41s
Throughput
17 tps
Context
256K
$/Mtok
$0.094 / $0.250
venice/fp8fp8
Parasail99.69%
Healthy24h 99.23%
7d
99.09%
30d
99.09%
p50
702ms
p99
7.79s
Throughput
25 tps
Context
131K
$/Mtok
$0.090 / $0.300
parasail/bf16bf16
DeepInfra—
No data24h 98.35%
7d
96.95%
30d
96.95%
p50
408ms
p99
2.99s
Throughput
23 tps
Context
128K
$/Mtok
$0.075 / $0.200
deepinfra/fp8fp8

Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

1 endpoint reporting no data is omitted from the charts.

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.