# Sources (accessed 2026-08-04):
# https://www.qwencloud.com/models/qwen3.8-max
# https://docs.qwencloud.com/developer-guides/text-generation/thinking
# https://docs.qwencloud.com/developer-guides/getting-started/text-generation-models
# https://help.aliyun.com/zh/model-studio/model-pricing (Singapore: qwen3.8-max list)
# Toggle: enable_thinking true|false (hybrid)
# Effort: reasoning_effort = low|medium|xhigh (default xhigh); high accepted as alias → xhigh
# Budget: thinking_budget (0..262144) cannot be combined with reasoning_effort
# API: {"enable_thinking":true,"reasoning_effort":"medium"} or
# {"enable_thinking":true,"thinking_budget":16384}
# Pay-as-you-go on DashScope/QwenCloud (not Token Plan only). Cost USD/MTok from model page.
base_model = "alibaba/qwen3.8-max"
structured_output = true
reasoning_options = [
  { type = "toggle" },
  { type = "effort", values = ["low", "medium", "xhigh"] },
  { type = "budget_tokens", min = 0, max = 262_144 },
]

[interleaved]
field = "reasoning_content"

[cost]
input = 2.00
output = 6.00
cache_read = 0.25
cache_write = 2.5