GLM 5.2 - GENGEN API

A text generation model for chat completions with support for large reasoning-token budgets.

Model ID

glm-5-2-260617

Pass this exact public ID in the top-level model field. Do not substitute an upstream provider alias.

Function calling
Online inference
Streaming output
Context caching See Function calling and Gemini tools for tool declarations, result submission, and provider-specific capabilities.

Property	Value
Provider	`byteplus-modelark`
Modality	`reasoning`
Processing	`Synchronous response`
Endpoint	`/api/gengen/v1/chat/completions`
Rate limit	`0.5K`
Context window	`1024K`
Streaming	`Supported (Server-Sent Events)`
Max input tokens	`1024K`
Max output tokens	`128K`
Max reasoning tokens	`128K`
Token rate limit	`1000K`

Availability and final customer prices can change. Check the Dashboard model catalog before production use.

See the API reference overview for authentication, request conventions, and response schemas.