Model scorecard

Anthropic claude-sonnet-4.5

Composite 69.0/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.

B+69.0/100anthropic/claude-sonnet-4.5text · vision · 200k context

eval composite

Quality (blended eval)91

Category: coding

Usable context10

200k advertised window

gateway measured

Throughput34

118 output tokens/s median

Time to first token63

220ms p50

at provider cost

Price efficiency64

$3.00 per 1M output tokens

Quality per dollar91

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.
Function calling & agentsauto:tools
Schema conformance under a wide tool set matters more than raw reasoning score.
High-volume product chatauto:cost + cache
Semantic caching does more for the bill here than any model swap.