FW-GLM-5.3

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-5.3 is Z.ai's flagship model for complex software engineering and agent capabilities. It uses the same base model as GLM-5.2, with its improvements driven by expanded post-training across more diverse long-horizon task environments. The model supports text-only input, a 1,048,576-token context window, and a maximum output length of 131,072 tokens. Reasoning is always enabled and can be configured with low, high, or max effort levels. GLM-5.3 also supports streaming, function calling, context caching, and structured output.

Key model capabilities

• 1M-token context window and 128K-token maximum output
• Strong complex software engineering and long-horizon task capabilities
• Always-on reasoning with low, high, and max effort levels
• Function calling and tool use
• Streaming responses
• Context caching for long-context conversations
• Structured output support