FW-GLM-5.2

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Non-Microsoft Product. The following terms apply to a Customer's use of Fireworks on Foundry: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, Customer Data will be sent outside of Microsoft systems, Customer Data will not be processed pursuant to any Foundry data residency documentation, and different compliance and data handling rules will apply. See Trust Center - Fireworks AI for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization's compliance requirements.

About this model

GLM-5.2 is Z.ai's latest flagship model for long-horizon tasks. It delivers a solid 1M-token context window, stronger coding capabilities with multiple thinking effort levels, and architectural improvements for efficient long-context inference. GLM-5.2 uses the GLM MoE DSA architecture and introduces IndexShare, which reuses the same indexer across every four sparse attention layers and reduces per-token FLOPs by 2.9x at a 1M context length. The MTP layer for speculative decoding is also improved, increasing acceptance length by up to 20%. The model is released under an MIT open-source license.

Key model capabilities

• 1M-token context window for long-horizon work
• Advanced coding with flexible thinking effort levels
• GLM MoE DSA architecture with IndexShare for efficient sparse attention
• Improved MTP layer for speculative decoding
• Reasoning and thinking capabilities
• Function calling and tool use
• Multilingual support (English and Chinese)
• Streaming support