Model scorecard
DeepSeek deepseek-r1-distill-70b
Composite 70.2/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+70.2/100deepseek/deepseek-r1-distill-70btext · 128k context
Capability
eval compositeQuality (blended eval)83
Category: reasoning
Usable context6
128k advertised window
Serving
gateway measuredThroughput47
165 output tokens/s median
Time to first token70
180ms p50
Economics
at provider costPrice efficiency83
$0.35 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
Not a default pick today. It is a reasonable explicit choice when you need this vendor specifically, or as a failover target inside auto:reasoning.
→ Full workload matrix