data/2024-01-26 16:21:10.212177_model_costs.csv

model,provider,provider_pricing,cost_per_token
gpt-3.5-turbo,OpenAI,"$1 / 1M input tokens, $2 / 1M output tokens","$1 / 1M input tokens, $2 / 1M output tokens"
gpt-4-turbo,OpenAI,"$10 / 1M input tokens, $30 / 1M output tokens","$10 / 1M input tokens, $30 / 1M output tokens"
gpt-4,OpenAI,"$30 / 1M input tokens, $60 / 1M output tokens","$30 / 1M input tokens, $60 / 1M output tokens"
gpt-3.5-turbo,OpenAI,"$1 / 1M input tokens, $2 / 1M output tokens","$1 / 1M input tokens, $2 / 1M output tokens"
llama-2-70b-chat,Together AI,$0.2 / 1M tokens,$0.2 / 1M tokens
Mixtral-8x7B-Instruct-v0.1,Together AI,$0.9 / 1M tokens,$0.9 / 1M tokens
zephyr-7b-beta,Hugging Face Inference Endpoint,$1.3 / hour,$54 / 1M tokens
Mistral-7B-Instruct-v0.2,Hugging Face Inference Endpoint,$1.3 / hour,$53 / 1M tokens
TinyLlama/TinyLlama-1.1B-Chat-v1.0,Hugging Face Inference Endpoint,$0.6 / hour,$11 / 1M tokens
gemini-pro,Google VertexAI,"$0.25 / 1M input characters, $0.5 / 1M output characters (60 queries per minute are free)","$0.25 / 1M input tokens, $0.5 / 1M output tokens"
chat-bison (PaLM 2),Google VertexAI,"$0.25 / 1M input tokens, $0.5 / 1M output tokens","$0.25 / 1M input tokens, $0.5 / 1M output tokens"
chat-bison-32k (PaLM 2 32K),Google VertexAI,"$0.25 / 1M input tokens, $0.5 / 1M output tokens","$0.25 / 1M input tokens, $0.5 / 1M output tokens"