PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1521mPRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7921mPRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06621mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4521mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9721mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8121mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008621mPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004221mPRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4021mPRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1321mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01221mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01221mPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8052mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0052mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9852mPRICE~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

MiniMax M3

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

MiniMax M3 provider ranking

#1 OverallTogether97.3FastestTogether3.57 sBest valueTogetherEurope #1Cortecs92.1Best toolsTogether100.0%Best structuredCortecs100.0%
#ProviderΔ30d
01TogetherBEST OVERALL● MEASUREDUS · Serverless · MiniMax M3100.0%100.0%97.6%54217363.6s132P100↓ 1.3
02CortecsBEST EUROPEANEU RESIDENT● MEASUREDAT · Routed · MiniMax M3100.0%100.0%100.0%51759625.0s90P67↓ 0.1
03OpenRouter● MEASUREDUS · Routed · MiniMax M399.5%100.0%97.6%92930336.2s75P33↓ 0.2
3 of 5 providers ranked · · Methodology →
01Together97.3
Best overallUS · Serverless · MiniMax M3
TTFT542 ms
Rel.100.0%
Tok/s132
$ Out$1.20
Tools100.0%
Δ30d-1.3
View dossier
02Cortecs92.1
Best EuropeanAT · Routed · MiniMax M3
TTFT517 ms
Rel.100.0%
Tok/s90
$ Out$1.23
Tools100.0%
Δ30d-0.1
View dossier
03OpenRouter80.4
US · Routed · MiniMax M3
TTFT929 ms
Rel.99.5%
Tok/s75
$ Out$1.20
Tools100.0%
Δ30d-0.2
View dossier
3 of 5 providers ranked · · Methodology →
MiniMax M3 inference benchmark: fastest & cheapest providers · InferenceBench