fireworks/glm-5p2

Common Name: GLM-5.2

Fireworks
SupportedTool InvocationSupportedReasoning
CompareTry in Chat

Zhipu AI's flagship reasoning model for long-context engineering and agentic tasks.

Specifications

Context
1048.6K
Maximum Output
131.1K
Inputtext
Outputtext

Performance (7-day Average)

Collecting…
Collecting…
Collecting…

Pricing

Input$1.40/MTokens
Cached Input$0.14/MTokens
Output$4.40/MTokens

Availability Trend (24h)

Performance Metrics (24h)

Similar Models

$1.74/$3.48/M
ctx1.0Mmax384Kavailtps
InOutCap

DeepSeek's higher-capability hybrid-thinking model in the V4 family.

$1.00/$4.05/M
ctx1.0Mmaxavailtps
InOutCap

Thinking Machines Lab's general-purpose multimodal model with controllable reasoning effort.

$2.10/$6.60/M
ctx1.0Mmax131Kavailtps
InOutCap

Zhipu AI's accelerated flagship reasoning model for long-context engineering and agentic tasks.

$0.95/$4.00/M
ctx262Kmax262Kavailtps
InOutCap

Moonshot AI's multimodal reasoning model optimized for coding and agentic software engineering.