name = "Qwen Flash"
description = "Efficient Qwen model for fast chat, extraction, and high-volume workloads"
family = "qwen"
release_date = "2025-07-28"
last_updated = "2025-07-28"
attachment = false
reasoning = true
temperature = true
knowledge = "2024-04"
tool_call = true
open_weights = false

[[reasoning_options]]
type = "toggle"

[[reasoning_options]]
type = "budget_tokens"

[cost]
input = 0.05
output = 0.4

[limit]
context = 1_000_000
output = 32_768

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