# Sources (accessed 2026-08-28):
# https://www.qwencloud.com/models/qwen3.8-flash
# Pricing: $0.15 input / $0.47 output / cache read $0.016 / cache create $0.2
# per 1M tokens, flat. (Release blog quotes ~$0.16 input; model page prevails.)
# Toggle: enable_thinking true|false (hybrid)
# Effort: reasoning_effort = low|medium|xhigh (not yet in the API reference; see
# the Qwen3.8-Flash-Next release blog)
# Budget: thinking_budget (Max Reasoning 262K)
base_model = "alibaba/qwen3.8-flash"
reasoning_options = [
  { type = "toggle" },
  { type = "effort", values = ["low", "medium", "xhigh"] },
  { type = "budget_tokens", max = 262_144 },
]

[interleaved]
field = "reasoning_content"

[cost]
input = 0.15
output = 0.47
cache_read = 0.016
cache_write = 0.2