glm-5-turbo

Common Name: GLM-5 Turbo

Released on Mar 16 12:00 AMKnowledge Cutoff Apr 1, 2025 12:00 AMSupportedTool InvocationSupportedReasoning

GLM-5-Turbo is the fast variant of GLM-5, optimized for lower latency and cost while retaining strong agentic and coding performance.

Specifications

Context

200K

Maximum Output

128K

Inputtext

Outputtext

Performance (7-day Average)

Collecting…

Pricing

< 32K

Input¥5.50/MTokens

Output¥24.20/MTokens

Cached Input¥1.32/MTokens

32K-200K

Input¥7.70/MTokens

Output¥28.60/MTokens

Cached Input¥1.98/MTokens

Availability Trend (24h)

Performance Metrics (24h)

Similar Models

GLM-4.5 AirX

¥4.40/¥13.20/M

ctx128Kmax—avail—tps—

InOutCap

Zhipu AI's GLM-4.5 AirX variant optimized for high-speed inference.

GLM-4.5 X

¥8.80/¥17.60/M

ctx128Kmax—avail—tps—

InOutCap

Zhipu AI's GLM-4.5 X variant with enhanced performance.

GLM-5

¥4.40/¥19.80/M

ctx200Kmax128Kavail—tps—

InOutCap

GLM-5 is Zhipu AI's new-generation flagship base model (744B total / 40B active MoE), with significantly improved coding, reasoning, and agentic capabilities over GLM-4.7.

GLM-5.1

¥6.60/¥26.40/M

ctx200Kmax128Kavail—tps—

InOutCap

GLM-5.1 is Zhipu AI's flagship model aligned with Claude Opus 4.6 in capability, featuring an 8-hour long-horizon agent runtime and top-tier performance on complex engineering tasks.