# Sources (accessed 2026-09-28):
# https://www.alibabacloud.com/help/en/model-studio/qwen3-8-omni-flash
# https://www.alibabacloud.com/help/en/model-studio/model-pricing (Singapore)
# https://www.qwencloud.com/models/qwen3.8-omni-flash
# https://www.alibabacloud.com/help/en/model-studio/qwen-api-via-openai-chat-completions
# Effort: reasoning_effort = low|medium|xhigh; none disables thinking.
# This model uses implicit cache, not explicit cache creation.
base_model = "alibaba/qwen3.8-omni-flash"
reasoning_options = [{ type = "effort", values = ["none", "low", "medium", "xhigh"] }]

[interleaved]
field = "reasoning_content"

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