PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1514m PRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7914m PRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06614m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4514m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9714m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8114m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008614m PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004214m PRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4014m PRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1314m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01214m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01214m PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8045m PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0045m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9845m PRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.131h PRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.201h PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.101h PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751h PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361h PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291h PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.992h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.002h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.802h PERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%2h PERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%2h PERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%2h PERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%2h PERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%2h PERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%2h PERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%2h PERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%2h PERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%2h PERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%2h

PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1514m PRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7914m PRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06614m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4514m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9714m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8114m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008614m PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004214m PRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4014m PRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1314m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01214m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01214m PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8045m PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0045m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9845m PRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.131h PRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.201h PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.101h PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751h PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361h PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291h PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.992h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.002h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.802h PERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%2h PERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%2h PERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%2h PERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%2h PERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%2h PERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%2h PERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%2h PERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%2h PERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%2h PERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%2h

DeepSeek V4 Flash

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

DeepSeek V4 Flash provider ranking

#1 OverallScaleway99.0 FastestScaleway3.39 s Best valueOpenRouter Europe #1Scaleway99.0 Best 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%41112876.2s69P75↑ 6.0

03OpenRouterBEST VALUE● MEASUREDUS · Routed · DeepSeek V4 Flash100.0%100.0%92.9%105988635.6s89P100↓ 0.2

04Together● MEASUREDUS · Serverless · DeepSeek V4 Flash98.0%100.0%100.0%70419087.0s63P50↓ 4.8

4 of 8 providers ranked · · Methodology →

Sort

Best overallFR · Serverless · DeepSeek V4 Flash

TTFT389 ms

Rel.100.0%

Tok/s133

$ Out$0.92

Tools100.0%

Δ30d+17.1

AT · Routed · DeepSeek V4 Flash

TTFT411 ms

Rel.100.0%

Tok/s69

$ Out$0.18

Tools100.0%

Δ30d+6.0

03OpenRouter83.0

Best valueUS · Routed · DeepSeek V4 Flash

TTFT1059 ms

Rel.100.0%

Tok/s89

$ Out$0.06

Tools100.0%

Δ30d-0.2

US · Serverless · DeepSeek V4 Flash

TTFT704 ms

Rel.98.0%

Tok/s63

$ Out$0.28

Tools100.0%

Δ30d-4.8

4 of 8 providers ranked · · Methodology →

DeepSeek V4 Flash inference benchmark: fastest & cheapest providers · InferenceBench