Model scorecard
DeepSeek deepseek-r1
Composite 67.8/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+67.8/100deepseek/deepseek-r1text · 128k context
Capability
eval compositeQuality (blended eval)88
Category: reasoning
Usable context6
128k advertised window
Serving
gateway measuredThroughput26
90 output tokens/s median
Time to first token47
320ms p50
Economics
at provider costPrice efficiency79
$0.55 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
- Deep reasoning & mathauto:reasoning
Reasoning tokens dominate the bill, so quality per thinking-token beats headline price.