Model scorecard
Meta llama-4-70b
Composite 70.6/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+70.6/100meta/llama-4-70btext · 128k context
Capability
eval compositeQuality (blended eval)81
Category: cheap
Usable context6
128k advertised window
Serving
gateway measuredThroughput63
220 output tokens/s median
Time to first token82
110ms p50
Economics
at provider costPrice efficiency75
$0.90 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
- Realtime & voice turnsauto:speed
TTFT is the whole experience; specialty silicon beats a smarter model that starts late.