PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.292mPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.362mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.752mPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.102mPRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.202mPRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.132mPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8033mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0033mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9933mPERFORMANCEGLM-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 0.00111h

MiniMax M3

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

MiniMax M3 provider ranking

#1 OverallTogether96.3FastestTogether3.57 sBest valueTogetherEurope #1Cortecs91.2Best 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 →
01Together96.3
Best overallUS · Serverless · MiniMax M3
TTFT542 ms
Rel.100.0%
Tok/s132
$ Out$1.20
Tools100.0%
Δ30d-1.3
View dossier
02Cortecs91.2
Best EuropeanAT · Routed · MiniMax M3
TTFT517 ms
Rel.100.0%
Tok/s90
$ Out$1.23
Tools100.0%
Δ30d-0.1
View dossier
03OpenRouter79.6
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