# DeepSeek V4 模型档案
family: deepseek_v4

variants:
  flash:
    display_name: DeepSeek V4 Flash
    model_id: deepseek/deepseek-v4-flash
    api_base: https://api.deepseek.com/v1
    api_key_env: DEEPSEEK_API_KEY
    max_context: 1048576
    reliable_context: 262144
    max_output: 8192       # 官方上限 384K；zcbot 先保留稳定输出预算，压测后再放大
    parallel_tools: false
    tool_calling_quality: good
    thinking_enabled: true
    thinking_transport: extra_body
    reasoning_effort_levels: [low, high, max]
    default_reasoning_effort: high
    reasoning_replay: tool_calls  # 普通跨轮剥离；工具调用 reasoning 按官方协议完整回传
    code_quality: good
    enable_run_python: true
    max_iterations: 120   # backstop 兜底,非"轮"预算;真正的空转防护是 loop 的无进展熔断 + _RepeatGuard
    optimal_temperature: 0.3
    prompt_caching: false
    extended_thinking: false
    # Flash-0731 官方美元价按 1 USD ~= 7.2 CNY 折算；峰谷价正式生效后再同步。
    input_cny_per_mtoken: 1.0
    output_cny_per_mtoken: 2.0
    cache_hit_cny_per_mtoken: 0.02  # 官方 $0.0028 / M tokens

  pro:
    display_name: DeepSeek V4 Pro
    model_id: deepseek/deepseek-v4-pro
    api_base: https://api.deepseek.com/v1
    api_key_env: DEEPSEEK_API_KEY
    max_context: 1048576
    reliable_context: 524288
    max_output: 8192
    parallel_tools: true
    tool_calling_quality: excellent
    thinking_enabled: true
    thinking_transport: extra_body
    reasoning_effort_levels: [low, medium, high, max]
    default_reasoning_effort: medium
    reasoning_replay: tool_calls
    code_quality: excellent
    enable_run_python: true
    max_iterations: 150   # backstop 兜底,非"轮"预算;真正的空转防护是 loop 的无进展熔断 + _RepeatGuard
    optimal_temperature: 0.2
    prompt_caching: false
    extended_thinking: false
    input_cny_per_mtoken: 2.0
    output_cny_per_mtoken: 20.0
    cache_hit_cny_per_mtoken: 0.2   # DeepSeek 前缀缓存命中价(input 的 ~0.1x)