# Native `/ai/run` accepts `reasoning_effort = low|medium|high` and
# `chat_template_kwargs.enable_thinking = true|false`; no budget is documented.
# https://developers.cloudflare.com/workers-ai/models/glm-4.7-flash/sync-input.json (accessed 2026-06-25)

name = "GLM-4.7-Flash"
description = "Efficient GLM model for fast reasoning, coding, and agent workflows"
family = "glm-flash"
release_date = "2026-01-19"
last_updated = "2026-01-19"
attachment = false
reasoning = true
reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["low", "medium", "high"] }]
temperature = true
tool_call = true
structured_output = true
knowledge = "2025-04"
open_weights = true

[interleaved]
field = "reasoning_content"

[cost]
input = 0.0605
output = 0.4

[limit]
context = 131_072
output = 131_072

[modalities]
input = ["text"]
output = ["text"]