PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1515mPRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7915mPRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06615mPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4515mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9715mPRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8115mPRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008615mPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004215mPRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4015mPRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1315mPRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01215mPRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01215mPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8046mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0046mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9846mPRICE~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

GLM-5.2

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

GLM-5.2 provider ranking

#1 OverallTogether100.0FastestTogether1.68 sBest valueCortecsEurope #1Cortecs92.1Best toolsTogether100.0%Best structuredTogether100.0%
#ProviderΔ30d
01TogetherBEST OVERALL● MEASUREDUS · Serverless · GLM-5.2100.0%100.0%100.0%2715891.7s283P50↑ 0.8
02CortecsBEST VALUEEU RESIDENT● MEASUREDAT · Routed · GLM-5.2100.0%100.0%100.0%42520673.2s142P100↑ 7.1
03ScalewayEU RESIDENTEU OWNED● MEASUREDFR · Serverless · GLM-5.2100.0%100.0%100.0%28216304.7s91P25↑ 12.0
04OpenRouter● MEASUREDUS · Routed · GLM-5.299.1%100.0%71.4%48011313.4s137P75↓ 2.9
4 of 9 providers ranked · · Methodology →
01Together100.0
Best overallUS · Serverless · GLM-5.2
TTFT271 ms
Rel.100.0%
Tok/s283
$ Out$4.40
Tools100.0%
Δ30d+0.8
View dossier
02Cortecs92.1
Best valueAT · Routed · GLM-5.2
TTFT425 ms
Rel.100.0%
Tok/s142
$ Out$3.33
Tools100.0%
Δ30d+7.1
View dossier
03Scaleway84.2
FR · Serverless · GLM-5.2
TTFT282 ms
Rel.100.0%
Tok/s91
$ Out$6.30
Tools100.0%
Δ30d+12.0
View dossier
04OpenRouter76.7
US · Routed · GLM-5.2
TTFT480 ms
Rel.99.1%
Tok/s137
$ Out$3.99
Tools100.0%
Δ30d-2.9
View dossier
4 of 9 providers ranked · · Methodology →
GLM-5.2 inference benchmark: fastest & cheapest providers · InferenceBench