# 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_turn  # 只在当前用户轮次的工具链内原样回传 reasoning
    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
    # 扁平价保留给旧调用方，取当前谷时折算值；正式记账使用下面的版本化 pricing。
    input_cny_per_mtoken: 1.584
    output_cny_per_mtoken: 4.752
    cache_hit_cny_per_mtoken: 0.0504
    pricing:
      periods:
        - revision: deepseek-v4-20260816
          currency: USD
          fx_to_cny: 7.2
          source_url: https://api-docs.deepseek.com/quick_start/pricing/
          checked_at: 2026-08-30
          effective_from: 2026-08-16T16:00:00Z
          default:  # 谷时（官方峰时之外）
            input_per_mtoken: 0.22
            cache_hit_per_mtoken: 0.007
            output_per_mtoken: 0.66
          time_tiers:
            - name: peak
              timezone: UTC
              weekdays: [mon, tue, wed, thu, fri]
              windows:
                - ["01:00", "04:00"]
                - ["06:00", "10:00"]
              input_per_mtoken: 0.44
              cache_hit_per_mtoken: 0.014
              output_per_mtoken: 1.32

  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_turn
    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: 4.752
    output_cny_per_mtoken: 14.256
    cache_hit_cny_per_mtoken: 0.1584
    pricing:
      periods:
        - revision: deepseek-v4-20260816
          currency: USD
          fx_to_cny: 7.2
          source_url: https://api-docs.deepseek.com/quick_start/pricing/
          checked_at: 2026-08-30
          effective_from: 2026-08-16T16:00:00Z
          default:
            input_per_mtoken: 0.66
            cache_hit_per_mtoken: 0.022
            output_per_mtoken: 1.98
          time_tiers:
            - name: peak
              timezone: UTC
              weekdays: [mon, tue, wed, thu, fri]
              windows:
                - ["01:00", "04:00"]
                - ["06:00", "10:00"]
              input_per_mtoken: 1.32
              cache_hit_per_mtoken: 0.044
              output_per_mtoken: 3.96