Model scorecard
DeepSeek deepseek-coder-v2
Composite 70.4/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+70.4/100deepseek/deepseek-coder-v2text · 128k context
Capability
eval compositeQuality (blended eval)83
Category: coding
Usable context6
128k advertised window
Serving
gateway measuredThroughput49
170 output tokens/s median
Time to first token70
180ms p50
Economics
at provider costPrice efficiency82
$0.40 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:coding.
→ Full workload matrix