Agent/config/pricing.yaml

# LLM 定价配置
#
# 价格单位：美元 / 1M tokens
# 支持通配符：* 匹配任意字符
#
# 字段说明：
#   model: 模型名称（必填）
#   input_price: 输入 token 价格（必填）
#   output_price: 输出 token 价格（必填）
#   reasoning_price: 推理 token 价格（可选，默认 = output_price）
#   cache_creation_price: 缓存创建价格（可选，默认 = input_price * 1.25）
#   cache_read_price: 缓存读取价格（可选，默认 = input_price * 0.1）
#   provider: 提供商名称（可选，用于分类）
#   description: 描述（可选）
#
# 使用方法：
#   1. 复制此文件到项目根目录或 config/ 目录
#   2. 或设置环境变量 AGENT_PRICING_CONFIG 指向配置文件
#   3. 根据实际使用的模型修改价格

models:
  # ===== OpenAI =====
  - model: gpt-4o
    input_price: 2.50
    output_price: 10.00
    provider: openai

  - model: gpt-4o-mini
    input_price: 0.15
    output_price: 0.60
    provider: openai

  - model: gpt-4-turbo
    input_price: 10.00
    output_price: 30.00
    provider: openai

  # o1 系列（有 reasoning tokens）
  - model: o1
    input_price: 15.00
    output_price: 60.00
    reasoning_price: 60.00  # reasoning tokens 和 output 同价
    provider: openai

  - model: o1-mini
    input_price: 3.00
    output_price: 12.00
    reasoning_price: 12.00
    provider: openai

  - model: o3-mini
    input_price: 1.10
    output_price: 4.40
    reasoning_price: 4.40
    provider: openai

  # ===== Anthropic Claude =====
  # Claude 支持 prompt caching，缓存价格：
  #   - cache_creation: 1.25x input_price
  #   - cache_read: 0.1x input_price
  - model: claude-3-5-sonnet-20241022
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75   # 3.00 * 1.25
    cache_read_price: 0.30       # 3.00 * 0.1
    provider: anthropic

  - model: claude-3-5-haiku-20241022
    input_price: 0.80
    output_price: 4.00
    cache_creation_price: 1.00   # 0.80 * 1.25
    cache_read_price: 0.08       # 0.80 * 0.1
    provider: anthropic

  - model: claude-3-opus-20240229
    input_price: 15.00
    output_price: 75.00
    cache_creation_price: 18.75  # 15.00 * 1.25
    cache_read_price: 1.50       # 15.00 * 0.1
    provider: anthropic

  # Claude 通配符（匹配新版本）
  - model: claude-3-5-sonnet*
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75
    cache_read_price: 0.30
    provider: anthropic

  - model: claude-sonnet-4*
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75   # 3.00 * 1.25
    cache_read_price: 0.30       # 3.00 * 0.1
    provider: anthropic

  - model: claude-opus-4*
    input_price: 5.00
    output_price: 25.00
    cache_creation_price: 6.25   # 5.00 * 1.25
    cache_read_price: 0.50       # 5.00 * 0.1
    provider: anthropic

  # ===== Google Gemini =====
  - model: gemini-2.5-pro
    input_price: 1.25
    output_price: 10.00
    reasoning_price: 10.00  # thinking mode
    provider: google

  - model: gemini-2.0-flash
    input_price: 0.10
    output_price: 0.40
    provider: google

  - model: gemini-2.0-flash-thinking
    input_price: 0.10
    output_price: 0.40
    reasoning_price: 0.40
    provider: google

  - model: gemini-1.5-pro
    input_price: 1.25
    output_price: 5.00
    provider: google

  - model: gemini-1.5-flash
    input_price: 0.075
    output_price: 0.30
    provider: google

  # Gemini 通配符
  - model: gemini-2.5*
    input_price: 1.25
    output_price: 10.00
    provider: google

  - model: gemini-2.0*
    input_price: 0.10
    output_price: 0.40
    provider: google

  # ===== DeepSeek =====
  - model: deepseek-chat
    input_price: 0.14
    output_price: 0.28
    provider: deepseek

  - model: deepseek-reasoner
    input_price: 0.55
    output_price: 2.19
    reasoning_price: 2.19
    provider: deepseek

  - model: deepseek-r1*
    input_price: 0.55
    output_price: 2.19
    reasoning_price: 2.19
    provider: deepseek

  # ===== OpenRouter 转发 =====
  # OpenRouter 使用 provider/model 格式
  - model: anthropic/claude-sonnet-4.5
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75
    cache_read_price: 0.30
    provider: openrouter

  - model: anthropic/claude-opus-4.5
    input_price: 5.00
    output_price: 25.00
    cache_creation_price: 6.25
    cache_read_price: 0.50
    provider: openrouter

  - model: anthropic/claude-opus-4.6
    input_price: 5.00
    output_price: 25.00
    cache_creation_price: 6.25
    cache_read_price: 0.50
    provider: openrouter

  - model: anthropic/claude-haiku-4.5
    input_price: 1.00
    output_price: 5.00
    cache_creation_price: 1.25
    cache_read_price: 0.10
    provider: openrouter

  - model: anthropic/claude-sonnet-4
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75
    cache_read_price: 0.30
    provider: openrouter

  - model: anthropic/claude*
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75
    cache_read_price: 0.30
    provider: openrouter

  - model: openai/gpt-4o*
    input_price: 2.50
    output_price: 10.00
    provider: openrouter

  - model: openai/o1*
    input_price: 15.00
    output_price: 60.00
    reasoning_price: 60.00
    provider: openrouter

  - model: google/gemini-3-pro-preview
    input_price: 2
    output_price: 12
    reasoning_price: 12
    provider: openrouter

  - model: google/gemini-3-flash-preview
    input_price: 0.50
    output_price: 3
    reasoning_price: 3
    provider: openrouter

  - model: google/gemini*
    input_price: 0.30
    output_price: 2.50
    reasoning_price: 2.50
    provider: openrouter

  - model: deepseek/deepseek-r1*
    input_price: 0.55
    output_price: 2.19
    reasoning_price: 2.19
    provider: openrouter

  # ===== Yescode 代理 =====
  - model: claude-sonnet-4.5
    input_price: 3.00
    output_price: 15.00
    cache_creation_price: 3.75
    cache_read_price: 0.30
    provider: yescode