Model scorecard
Anthropic claude-haiku-4.5
Composite 71.5/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+71.5/100anthropic/claude-haiku-4.5text · vision · 200k context
Capability
eval compositeQuality (blended eval)84
Category: cheap
Usable context10
200k advertised window
Serving
gateway measuredThroughput56
195 output tokens/s median
Time to first token78
130ms p50
Economics
at provider costPrice efficiency76
$0.80 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
- Batch classification & extractionauto:cost
At this volume a 3x price difference dwarfs a 2-point quality difference.