llmcloud.ai
Model scorecard

Mistral codestral-2508

Composite 72.4/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.

A72.4/100mistral/codestral-2508text · 256k context

Capability

eval composite
Quality (blended eval)82

Category: coding

Usable context13

256k advertised window

Serving

gateway measured
Throughput57

200 output tokens/s median

Time to first token80

120ms p50

Economics

at provider cost
Price efficiency82

$0.40 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:coding.

→ Full workload matrix