PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8031mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0031mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9931mPERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%1hPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%1hPERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%1hPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%1hPERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%1hPERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%1hPERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%1hPERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%1hPERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%1hPERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%1hPERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%1hPERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%1hPERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%1hPERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%1hPERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%1hPERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%1hPERFORMANCEGLM-4.7 via OpenRouter: TTFT ↓ 78%1hPERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 24%1hPERFORMANCEKimi K3 → Together AI: TTFT ↓ 34%1hPERFORMANCEDeepSeek V4 Flash via OpenRouter: throughput ↓ 17%1hPERFORMANCELlama 3.3 70B via Cortecs: TTFT ↓ 51%1hPERFORMANCEQwen3 235B via OpenRouter: throughput ↑ 37%1hPERFORMANCEQwen3 235B via OpenRouter: TTFT ↓ 29%1hPERFORMANCEDeepSeek V4 Flash → Together AI: throughput ↑ 19%1hPERFORMANCEGLM-5.3 via OpenRouter: throughput ↓ 17%1hPERFORMANCEGPT-OSS 20B via Cortecs: throughput ↑ 28%1hPERFORMANCELlama 3.3 70B → Together AI: TTFT ↓ 33%1hPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291hPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.00111hPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.28 to 1.041hPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok decreased from 0.0077 to 0.00381hPRICEz-ai/glm-5.1 cached_input_per_mtok increased from 0.18 to 0.261hPRICEz-ai/glm-5.1 output_per_mtok increased from 3.03 to 4.401hPRICEz-ai/glm-5.1 input_per_mtok increased from 0.96 to 1.401hPRICEtencent/hy4-preview cached_input_per_mtok increased from 0.038 to 0.0421h

DeepSeek V4 Flash

8 providers · MoE · 1.3M context · 2 regions · all models →

DeepSeek V4 Flash provider ranking

#1 OverallScaleway99.0FastestScaleway3.39 sBest valueOpenRouterEurope #1Scaleway99.0Best toolsScaleway100.0%Best structuredScaleway100.0%
#ProviderΔ30d
01ScalewayBEST OVERALLEU RESIDENT● MEASUREDFR · Serverless · DeepSeek V4 Flash100.0%100.0%100.0%38933143.4s133P25↑ 17.1
02CortecsEU RESIDENTEU OWNED● MEASUREDAT · Routed · DeepSeek V4 Flash100.0%100.0%100.0%41112635.9s73P75↑ 6.0
03OpenRouterBEST VALUE● MEASUREDUS · Routed · DeepSeek V4 Flash100.0%100.0%92.9%105988635.6s89P100↓ 0.2
04Together● MEASUREDUS · Serverless · DeepSeek V4 Flash98.2%100.0%100.0%70718667.0s63P50↓ 4.8
4 of 8 providers ranked · · Methodology →
01Scaleway99.0
Best overallFR · Serverless · DeepSeek V4 Flash
TTFT389 ms
Rel.100.0%
Tok/s133
$ Out$0.92
Tools100.0%
Δ30d+17.1
View dossier
02Cortecs88.8
AT · Routed · DeepSeek V4 Flash
TTFT411 ms
Rel.100.0%
Tok/s73
$ Out$0.18
Tools100.0%
Δ30d+6.0
View dossier
03OpenRouter82.2
Best valueUS · Routed · DeepSeek V4 Flash
TTFT1059 ms
Rel.100.0%
Tok/s89
$ Out$0.06
Tools100.0%
Δ30d-0.2
View dossier
04Together77.5
US · Serverless · DeepSeek V4 Flash
TTFT707 ms
Rel.98.2%
Tok/s63
$ Out$0.28
Tools100.0%
Δ30d-4.8
View dossier
4 of 8 providers ranked · · Methodology →
DeepSeek V4 Flash inference benchmark: fastest & cheapest providers · InferenceBench