Model scorecard
DeepSeek deepseek-v4
Composite 71.9/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+71.9/100deepseek/deepseek-v4text · 128k context
Capability
eval compositeQuality (blended eval)90
Category: cheap
Usable context6
128k advertised window
Serving
gateway measuredThroughput40
140 output tokens/s median
Time to first token65
210ms p50
Economics
at provider costPrice efficiency79
$0.55 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
- High-volume product chatauto:cost + cache
Semantic caching does more for the bill here than any model swap.