llmcloud.ai
Model scorecard

Cohere command-a-03-2025

Composite 66.0/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.

B+66.0/100cohere/command-a-03-2025text · 256k context

Capability

eval composite
Quality (blended eval)83

Category: reasoning

Usable context13

256k advertised window

Serving

gateway measured
Throughput37

130 output tokens/s median

Time to first token63

220ms p50

Economics

at provider cost
Price efficiency66

$2.50 per 1M output tokens

Quality per dollar99
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:reasoning.

→ Full workload matrix