PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1519mPRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7919mPRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06619mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4519mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9719mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8119mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008619mPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004219mPRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4019mPRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1319mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01219mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01219mPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8050mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0050mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9850mPRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.131hPRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.201hPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.101hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751hPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361hPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291hPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.992hPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.002hPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.802hPERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%2hPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%2hPERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%2hPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%2hPERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%2hPERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%2hPERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%2hPERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%2hPERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%2hPERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%2hPERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%2hPERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%2hPERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%2hPERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%2hPERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%2hPERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%2h

DeepSeek V4 Pro

5 providers · MoE · 1M context · 2 regions · all models →

DeepSeek V4 Pro provider ranking

#1 OverallCortecs97.3FastestCortecs3.35 sBest valueOpenRouterEurope #1Cortecs97.3Best toolsCortecs100.0%Best structuredOpenRouter97.6%
#ProviderΔ30d
01CortecsBEST OVERALLEU RESIDENT● MEASUREDAT · Routed · DeepSeek V4 Pro100.0%100.0%95.2%48030193.3s140P50↓ 1.5
02OpenRouterBEST VALUE● MEASUREDUS · Routed · DeepSeek V4 Pro100.0%100.0%97.6%108634667.4s63P100↑ 5.8
2 of 5 providers ranked · · Methodology →
01Cortecs97.3
Best overallAT · Routed · DeepSeek V4 Pro
TTFT480 ms
Rel.100.0%
Tok/s140
$ Out$3.50
Tools100.0%
Δ30d-1.5
View dossier
02OpenRouter85.0
Best valueUS · Routed · DeepSeek V4 Pro
TTFT1086 ms
Rel.100.0%
Tok/s63
$ Out$0.42
Tools100.0%
Δ30d+5.8
View dossier
2 of 5 providers ranked · · Methodology →
DeepSeek V4 Pro inference benchmark: fastest & cheapest providers · InferenceBench