base_model = "deepseek/deepseek-v4-flash"
# Reasoning HTTP format (accessed 2026-06-25):
# This model toggles with `enable_thinking`: true or false. Chat Completions
# `reasoning_effort` accepts high (default) or max; low/medium map to high and
# xhigh maps to max. Anthropic Messages defaults `reasoning_effort` to max.
# Sources:
# https://www.alibabacloud.com/help/en/model-studio/deepseek-api
# https://www.alibabacloud.com/help/en/model-studio/anthropic-api-messages

reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["high", "max"] }]

[interleaved]
field = "reasoning_content"

[cost]
input = 0
output = 0
cache_read = 0