Model scorecard

Anthropic claude-opus-4.5

Composite 65.2/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.

B+65.2/100anthropic/claude-opus-4.5text · vision · 200k context

eval composite

Quality (blended eval)94

Category: reasoning

Usable context10

200k advertised window

gateway measured

Throughput23

82 output tokens/s median

Time to first token47

320ms p50

at provider cost

Price efficiency50

$15.00 per 1M output tokens

Quality per dollar19

llmcloud adds $0 to these token prices.

Suggested usage

Coding agentauto:coding
Highest diff fidelity per dollar; holds multi-file edits without re-reading the repo.
Deep reasoning & mathauto:reasoning
Reasoning tokens dominate the bill, so quality per thinking-token beats headline price.