api_cost/api_cost.yaml

# OpenAI
# https://openai.com/pricing


# ALL COSTS REPORTED PER 1,000 TOKENS
GPT_4_32K:
  in: 0.06
  out: 0.12
GPT_4:
  in: 0.03
  out: 0.06
# GPT_4_TURBO: ###############
#   in: 0.01
#   out: 0.03
GPT_4o_2024_05_13:
  in: 0.005
  out: 0.015
GPT_4o_mini_2024_07_18:
  in: 0.000150
  out: 0.000600
GPT_4_TURBO_2024_04_09:
  in: 0.01
  out: 0.03
GPT_4_TURBO_0125:
  in: 0.01
  out: 0.03
GPT_4_TURBO_1106:
  in: 0.01
  out: 0.03
GPT_3_5_INSTRUCT:
  in: 0.0015
  out: 0.0020
GPT_3_5:
  in: 0.0010
  out: 0.0020

# Azure
AZURE_GPT_4_32K:
  in: 0.06
  out: 0.12
AZURE_GPT_4:
  in: 0.03
  out: 0.06
AZURE_GPT_4_TURBO_1106:
  in: 0.01
  out: 0.03
AZURE_GPT_4_TURBO_0125:
  in: 0.01
  out: 0.03
AZURE_GPT_3_5_INSTRUCT:
  in: 0.0015
  out: 0.0020
AZURE_GPT_3_5:
  in: 0.0010
  out: 0.0020


# Google Gemini
# https://ai.google.dev/pricing
GEMINI_PRO:
  in: 0.0005
  out: 0.0015
GEMINI_1_5_FLASH:
  in: 0.00035
  out: 0.00105
GEMINI_1_5_PRO:
  in: 0.0035
  out: 0.0105

# Google PaLM 2 (text-bison, text-unicorn)
# https://cloud.google.com/vertex-ai/docs/generative-ai/pricing
PALM2_TU_1:
  in: 0.00025
  out: 0.00020
PALM2_TB_1:
  in: 0.00025
  out: 0.0005
PALM2_TB_2:
  in: 0.00025
  out: 0.0005


# Mistral AI 
# https://docs.mistral.ai/platform/pricing/
OPEN_MIXTRAL_8X7B:
  in: 0.0007
  out: 0.0007
OPEN_MISTRAL_7B:
  in: 0.000250
  out: 0.000250
MISTRAL_LARGE:
  in: 0.008
  out: 0.024
MISTRAL_MEDIUM:
  in: 0.0027
  out: 0.0081
MISTRAL_SMALL:
  in: 0.002
  out: 0.006


################
# Local Models
################
LOCAL_MIXTRAL_8X7B_INSTRUCT_V01:
  in: 0.0
  out: 0.0
LOCAL_MISTRAL_7B_INSTRUCT_V02: 
  in: 0.0
  out: 0.0
LOCAL_CPU_MISTRAL_7B_INSTRUCT_V02_GGUF:
  in: 0.0
  out: 0.0
phyloforfun/mistral-7b-instruct-v2-bnb-4bit__HLT_MICH_Angiospermae_SLTPvC_v1-0_medium_OCR-C25-L25-E50-R05:
  in: 0.0
  out: 0.0