llmcloud.ai
Model scorecard

Mistral pixtral-large

Composite 61.6/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.

B61.6/100mistral/pixtral-largetext · vision · 128k context

Capability

eval composite
Quality (blended eval)80

Category: vision

Usable context6

128k advertised window

Serving

gateway measured
Throughput29

100 output tokens/s median

Time to first token47

320ms p50

Economics

at provider cost
Price efficiency68

$2.00 per 1M output tokens

Quality per dollar100
llmcloud adds $0 to these token prices.

Suggested usage

Not a default pick today. It is a reasonable explicit choice when you need this vendor specifically, or as a failover target inside auto:vision.

→ Full workload matrix