tokencost

Clientside token counting + price estimation for LLM apps and AI agents.

🐦 Twitter   •   📢 Discord   •   🖇️ AgentOps

TokenCost

Tokencost helps calculate the USD cost of using major Large Language Model (LLMs) APIs by calculating the estimated cost of prompts and completions.

Building AI agents? Check out AgentOps

Features

• LLM Price Tracking Major LLM providers frequently add new models and update pricing. This repo helps track the latest price changes
• Token counting Accurately count prompt tokens before sending OpenAI requests
• Easy integration Get the cost of a prompt or completion with a single function

Example usage:

from tokencost import calculate_prompt_cost, calculate_completion_cost

model = "gpt-3.5-turbo"
prompt = [{ "role": "user", "content": "Hello world"}]
completion = "How may I assist you today?"

prompt_cost = calculate_prompt_cost(prompt, model)
completion_cost = calculate_completion_cost(completion, model)

print(f"{prompt_cost} + {completion_cost} = {prompt_cost + completion_cost}")
# 0.0000135 + 0.000014 = 0.0000275

Installation

Recommended: PyPI:

pip install tokencost

Usage

Cost estimates

Calculating the cost of prompts and completions from OpenAI requests

from openai import OpenAI

client = OpenAI()
model = "gpt-3.5-turbo"
prompt = [{ "role": "user", "content": "Say this is a test"}]

chat_completion = client.chat.completions.create(
    messages=prompt, model=model
)

completion = chat_completion.choices[0].message.content
# "This is a test."

prompt_cost = calculate_prompt_cost(prompt, model)
completion_cost = calculate_completion_cost(completion, model)
print(f"{prompt_cost} + {completion_cost} = {prompt_cost + completion_cost}")
# 0.0000180 + 0.000010 = 0.0000280

Calculating cost using string prompts instead of messages:

from tokencost import calculate_prompt_cost

prompt_string = "Hello world" 
response = "How may I assist you today?"
model= "gpt-3.5-turbo"

prompt_cost = calculate_prompt_cost(prompt_string, model)
print(f"Cost: ${prompt_cost}")
# Cost: $3e-06

Counting tokens

from tokencost import count_message_tokens, count_string_tokens

message_prompt = [{ "role": "user", "content": "Hello world"}]
# Counting tokens in prompts formatted as message lists
print(count_message_tokens(message_prompt, model="gpt-3.5-turbo"))
# 9

# Alternatively, counting tokens in string prompts
print(count_string_tokens(prompt="Hello world", model="gpt-3.5-turbo"))
# 2

How tokens are counted

Under the hood, strings and ChatML messages are tokenized using Tiktoken, OpenAI’s official tokenizer. Tiktoken splits text into tokens (which can be parts of words or individual characters) and handles both raw strings and message formats with additional tokens for message formatting and roles.

For Anthropic models above version 3 (i.e. Sonnet 3.5, Haiku 3.5, and Opus 3), we use the Anthropic beta token counting API to ensure accurate token counts. For older Claude models, we approximate using Tiktoken with the cl100k_base encoding.

Cost table

Units denominated in USD. All prices can be located here.

Model Name	Prompt Cost (USD) per 1M tokens	Completion Cost (USD) per 1M tokens	Max Prompt Tokens	Max Output Tokens
gpt-4	$30	$60	8192	4096
gpt-4o	$2.5	$10	128,000	16384
gpt-4o-audio-preview	$2.5	$10	128,000	16384
gpt-4o-audio-preview-2024-10-01	$2.5	$10	128,000	16384
gpt-4o-mini	$0.15	$0.6	128,000	16384
gpt-4o-mini-2024-07-18	$0.15	$0.6	128,000	16384
o1-mini	$1.1	$4.4	128,000	65536
o1-mini-2024-09-12	$3	$12	128,000	65536
o1-preview	$15	$60	128,000	32768
o1-preview-2024-09-12	$15	$60	128,000	32768
chatgpt-4o-latest	$5	$15	128,000	4096
gpt-4o-2024-05-13	$5	$15	128,000	4096
gpt-4o-2024-08-06	$2.5	$10	128,000	16384
gpt-4-turbo-preview	$10	$30	128,000	4096
gpt-4-0314	$30	$60	8,192	4096
gpt-4-0613	$30	$60	8,192	4096
gpt-4-32k	$60	$120	32,768	4096
gpt-4-32k-0314	$60	$120	32,768	4096
gpt-4-32k-0613	$60	$120	32,768	4096
gpt-4-turbo	$10	$30	128,000	4096
gpt-4-turbo-2024-04-09	$10	$30	128,000	4096
gpt-4-1106-preview	$10	$30	128,000	4096
gpt-4-0125-preview	$10	$30	128,000	4096
gpt-4-vision-preview	$10	$30	128,000	4096
gpt-4-1106-vision-preview	$10	$30	128,000	4096
gpt-3.5-turbo	$1.5	$2	16,385	4096
gpt-3.5-turbo-0301	$1.5	$2	4,097	4096
gpt-3.5-turbo-0613	$1.5	$2	4,097	4096
gpt-3.5-turbo-1106	$1	$2	16,385	4096
gpt-3.5-turbo-0125	$0.5	$1.5	16,385	4096
gpt-3.5-turbo-16k	$3	$4	16,385	4096
gpt-3.5-turbo-16k-0613	$3	$4	16,385	4096
ft:gpt-3.5-turbo	$3	$6	16,385	4096
ft:gpt-3.5-turbo-0125	$3	$6	16,385	4096
ft:gpt-3.5-turbo-1106	$3	$6	16,385	4096
ft:gpt-3.5-turbo-0613	$3	$6	4,096	4096
ft:gpt-4-0613	$30	$60	8,192	4096
ft:gpt-4o-2024-08-06	$3.75	$15	128,000	16384
ft:gpt-4o-mini-2024-07-18	$0.3	$1.2	128,000	16384
ft:davinci-002	$2	$2	16,384	4096
ft:babbage-002	$0.4	$0.4	16,384	4096
text-embedding-3-large	$0.13	$0	8,191	nan
text-embedding-3-small	$0.02	$0	8,191	nan
text-embedding-ada-002	$0.1	$0	8,191	nan
text-embedding-ada-002-v2	$0.1	$0	8,191	nan
text-moderation-stable	$0	$0	32,768	0
text-moderation-007	$0	$0	32,768	0
text-moderation-latest	$0	$0	32,768	0
256-x-256/dall-e-2	–	–	nan	nan
512-x-512/dall-e-2	–	–	nan	nan
1024-x-1024/dall-e-2	–	–	nan	nan
hd/1024-x-1792/dall-e-3	–	–	nan	nan
hd/1792-x-1024/dall-e-3	–	–	nan	nan
hd/1024-x-1024/dall-e-3	–	–	nan	nan
standard/1024-x-1792/dall-e-3	–	–	nan	nan
standard/1792-x-1024/dall-e-3	–	–	nan	nan
standard/1024-x-1024/dall-e-3	–	–	nan	nan
whisper-1	–	–	nan	nan
tts-1	–	–	nan	nan
tts-1-hd	–	–	nan	nan
azure/tts-1	–	–	nan	nan
azure/tts-1-hd	–	–	nan	nan
azure/whisper-1	–	–	nan	nan
azure/o1-mini	$1.21	$4.84	128,000	65536
azure/o1-mini-2024-09-12	$1.1	$4.4	128,000	65536
azure/o1-preview	$15	$60	128,000	32768
azure/o1-preview-2024-09-12	$15	$60	128,000	32768
azure/gpt-4o	$2.5	$10	128,000	16384
azure/gpt-4o-2024-08-06	$2.5	$10	128,000	16384
azure/gpt-4o-2024-05-13	$5	$15	128,000	4096
azure/global-standard/gpt-4o-2024-08-06	$2.5	$10	128,000	16384
azure/global-standard/gpt-4o-mini	$0.15	$0.6	128,000	16384
azure/gpt-4o-mini	$0.16	$0.66	128,000	16384
azure/gpt-4-turbo-2024-04-09	$10	$30	128,000	4096
azure/gpt-4-0125-preview	$10	$30	128,000	4096
azure/gpt-4-1106-preview	$10	$30	128,000	4096
azure/gpt-4-0613	$30	$60	8,192	4096
azure/gpt-4-32k-0613	$60	$120	32,768	4096
azure/gpt-4-32k	$60	$120	32,768	4096
azure/gpt-4	$30	$60	8,192	4096
azure/gpt-4-turbo	$10	$30	128,000	4096
azure/gpt-4-turbo-vision-preview	$10	$30	128,000	4096
azure/gpt-35-turbo-16k-0613	$3	$4	16,385	4096
azure/gpt-35-turbo-1106	$1	$2	16,384	4096
azure/gpt-35-turbo-0613	$1.5	$2	4,097	4096
azure/gpt-35-turbo-0301	$0.2	$2	4,097	4096
azure/gpt-35-turbo-0125	$0.5	$1.5	16,384	4096
azure/gpt-35-turbo-16k	$3	$4	16,385	4096
azure/gpt-35-turbo	$0.5	$1.5	4,097	4096
azure/gpt-3.5-turbo-instruct-0914	$1.5	$2	4,097	nan
azure/gpt-35-turbo-instruct	$1.5	$2	4,097	nan
azure/gpt-35-turbo-instruct-0914	$1.5	$2	4,097	nan
azure/mistral-large-latest	$8	$24	32,000	nan
azure/mistral-large-2402	$8	$24	32,000	nan
azure/command-r-plus	$3	$15	128,000	4096
azure/ada	$0.1	$0	8,191	nan
azure/text-embedding-ada-002	$0.1	$0	8,191	nan
azure/text-embedding-3-large	$0.13	$0	8,191	nan
azure/text-embedding-3-small	$0.02	$0	8,191	nan
azure/standard/1024-x-1024/dall-e-3	–	$0	nan	nan
azure/hd/1024-x-1024/dall-e-3	–	$0	nan	nan
azure/standard/1024-x-1792/dall-e-3	–	$0	nan	nan
azure/standard/1792-x-1024/dall-e-3	–	$0	nan	nan
azure/hd/1024-x-1792/dall-e-3	–	$0	nan	nan
azure/hd/1792-x-1024/dall-e-3	–	$0	nan	nan
azure/standard/1024-x-1024/dall-e-2	–	$0	nan	nan
azure_ai/jamba-instruct	$0.5	$0.7	70,000	4096
azure_ai/mistral-large	$4	$12	32,000	8191
azure_ai/mistral-small	$1	$3	32,000	8191
azure_ai/Meta-Llama-3-70B-Instruct	$1.1	$0.37	8,192	2048
azure_ai/Meta-Llama-3.1-8B-Instruct	$0.3	$0.61	128,000	2048
azure_ai/Meta-Llama-3.1-70B-Instruct	$2.68	$3.54	128,000	2048
azure_ai/Meta-Llama-3.1-405B-Instruct	$5.33	$16	128,000	2048
azure_ai/cohere-rerank-v3-multilingual	$0	$0	4,096	4096
azure_ai/cohere-rerank-v3-english	$0	$0	4,096	4096
azure_ai/Cohere-embed-v3-english	$0.1	$0	512	nan
azure_ai/Cohere-embed-v3-multilingual	$0.1	$0	512	nan
babbage-002	$0.4	$0.4	16,384	4096
davinci-002	$2	$2	16,384	4096
gpt-3.5-turbo-instruct	$1.5	$2	8,192	4096
gpt-3.5-turbo-instruct-0914	$1.5	$2	8,192	4097
claude-instant-1	$1.63	$5.51	100,000	8191
mistral/mistral-tiny	$0.25	$0.25	32,000	8191
mistral/mistral-small	$0.1	$0.3	32,000	8191
mistral/mistral-small-latest	$0.1	$0.3	32,000	8191
mistral/mistral-medium	$2.7	$8.1	32,000	8191
mistral/mistral-medium-latest	$0.4	$2	131,072	8191
mistral/mistral-medium-2312	$2.7	$8.1	32,000	8191
mistral/mistral-large-latest	$2	$6	128,000	128000
mistral/mistral-large-2402	$4	$12	32,000	8191
mistral/mistral-large-2407	$3	$9	128,000	128000
mistral/pixtral-12b-2409	$0.15	$0.15	128,000	128000
mistral/open-mistral-7b	$0.25	$0.25	32,000	8191
mistral/open-mixtral-8x7b	$0.7	$0.7	32,000	8191
mistral/open-mixtral-8x22b	$2	$6	65,336	8191
mistral/codestral-latest	$1	$3	32,000	8191
mistral/codestral-2405	$1	$3	32,000	8191
mistral/open-mistral-nemo	$0.3	$0.3	128,000	128000
mistral/open-mistral-nemo-2407	$0.3	$0.3	128,000	128000
mistral/open-codestral-mamba	$0.25	$0.25	256,000	256000
mistral/codestral-mamba-latest	$0.25	$0.25	256,000	256000
mistral/mistral-embed	$0.1	–	8,192	nan
deepseek-chat	$0.14	$0.28	128,000	4096
codestral/codestral-latest	$0	$0	32,000	8191
codestral/codestral-2405	$0	$0	32,000	8191
text-completion-codestral/codestral-latest	$0	$0	32,000	8191
text-completion-codestral/codestral-2405	$0	$0	32,000	8191
deepseek-coder	$0.14	$0.28	128,000	4096
groq/llama2-70b-4096	$0.7	$0.8	4,096	4096
groq/llama3-8b-8192	$0.05	$0.08	8,192	8192
groq/llama3-70b-8192	$0.59	$0.79	8,192	8192
groq/llama-3.1-8b-instant	$0.05	$0.08	128,000	8192
groq/llama-3.1-70b-versatile	$0.59	$0.79	8,192	8192
groq/llama-3.1-405b-reasoning	$0.59	$0.79	8,192	8192
groq/mixtral-8x7b-32768	$0.24	$0.24	32,768	32768
groq/gemma-7b-it	$0.07	$0.07	8,192	8192
groq/gemma2-9b-it	$0.2	$0.2	8,192	8192
groq/llama3-groq-70b-8192-tool-use-preview	$0.89	$0.89	8,192	8192
groq/llama3-groq-8b-8192-tool-use-preview	$0.19	$0.19	8,192	8192
cerebras/llama3.1-8b	$0.1	$0.1	128,000	128000
cerebras/llama3.1-70b	$0.6	$0.6	128,000	128000
friendliai/mixtral-8x7b-instruct-v0-1	$0.4	$0.4	32,768	32768
friendliai/meta-llama-3-8b-instruct	$0.1	$0.1	8,192	8192
friendliai/meta-llama-3-70b-instruct	$0.8	$0.8	8,192	8192
claude-instant-1.2	$0.16	$0.55	100,000	8191
claude-2	$8	$24	100,000	8191
claude-2.1	$8	$24	200,000	8191
claude-3-haiku-20240307	$0.25	$1.25	200,000	4096
claude-3-haiku-latest	$0.25	$1.25	200,000	4096
claude-3-opus-20240229	$15	$75	200,000	4096
claude-3-opus-latest	$15	$75	200,000	4096
claude-3-sonnet-20240229	$3	$15	200,000	4096
claude-3-5-sonnet-20240620	$3	$15	200,000	8192
claude-3-5-sonnet-20241022	$3	$15	200,000	8192
claude-3-5-sonnet-latest	$3	$15	200,000	8192
text-bison	–	–	8,192	2048
text-bison@001	–	–	8,192	1024
text-bison@002	–	–	8,192	1024
text-bison32k	$0.12	$0.12	8,192	1024
text-bison32k@002	$0.12	$0.12	8,192	1024
text-unicorn	$10	$28	8,192	1024
text-unicorn@001	$10	$28	8,192	1024
chat-bison	$0.12	$0.12	8,192	4096
chat-bison@001	$0.12	$0.12	8,192	4096
chat-bison@002	$0.12	$0.12	8,192	4096
chat-bison-32k	$0.12	$0.12	32,000	8192
chat-bison-32k@002	$0.12	$0.12	32,000	8192
code-bison	$0.12	$0.12	6,144	1024
code-bison@001	$0.12	$0.12	6,144	1024
code-bison@002	$0.12	$0.12	6,144	1024
code-bison32k	$0.12	$0.12	6,144	1024
code-bison-32k@002	$0.12	$0.12	6,144	1024
code-gecko@001	$0.12	$0.12	2,048	64
code-gecko@002	$0.12	$0.12	2,048	64
code-gecko	$0.12	$0.12	2,048	64
code-gecko-latest	$0.12	$0.12	2,048	64
codechat-bison@latest	$0.12	$0.12	6,144	1024
codechat-bison	$0.12	$0.12	6,144	1024
codechat-bison@001	$0.12	$0.12	6,144	1024
codechat-bison@002	$0.12	$0.12	6,144	1024
codechat-bison-32k	$0.12	$0.12	32,000	8192
codechat-bison-32k@002	$0.12	$0.12	32,000	8192
gemini-pro	$0.5	$1.5	32,760	8192
gemini-1.0-pro	$0.5	$1.5	32,760	8192
gemini-1.0-pro-001	$0.5	$1.5	32,760	8192
gemini-1.0-ultra	$0.5	$1.5	8,192	2048
gemini-1.0-ultra-001	$0.5	$1.5	8,192	2048
gemini-1.0-pro-002	$0.5	$1.5	32,760	8192
gemini-1.5-pro	$1.25	$5	2,097,152	8192
gemini-1.5-pro-002	$1.25	$5	2,097,152	8192
gemini-1.5-pro-001	$1.25	$5	1,000,000	8192
gemini-1.5-pro-preview-0514	$0.08	$0.31	1,000,000	8192
gemini-1.5-pro-preview-0215	$0.08	$0.31	1,000,000	8192
gemini-1.5-pro-preview-0409	$0.08	$0.31	1,000,000	8192
gemini-1.5-flash	$0.08	$0.3	1,000,000	8192
gemini-1.5-flash-exp-0827	$0	$0	1,000,000	8192
gemini-1.5-flash-002	$0.08	$0.3	1,048,576	8192
gemini-1.5-flash-001	$0.08	$0.3	1,000,000	8192
gemini-1.5-flash-preview-0514	$0.08	$0	1,000,000	8192
gemini-pro-experimental	$0	$0	1,000,000	8192
gemini-flash-experimental	$0	$0	1,000,000	8192
gemini-pro-vision	$0.5	$1.5	16,384	2048
gemini-1.0-pro-vision	$0.5	$1.5	16,384	2048
gemini-1.0-pro-vision-001	$0.5	$1.5	16,384	2048
medlm-medium	–	–	32,768	8192
medlm-large	–	–	8,192	1024
vertex_ai/claude-3-sonnet@20240229	$3	$15	200,000	4096
vertex_ai/claude-3-5-sonnet@20240620	$3	$15	200,000	8192
vertex_ai/claude-3-5-sonnet-v2@20241022	$3	$15	200,000	8192
vertex_ai/claude-3-haiku@20240307	$0.25	$1.25	200,000	4096
vertex_ai/claude-3-opus@20240229	$15	$75	200,000	4096
vertex_ai/meta/llama3-405b-instruct-maas	$0	$0	32,000	32000
vertex_ai/meta/llama3-70b-instruct-maas	$0	$0	32,000	32000
vertex_ai/meta/llama3-8b-instruct-maas	$0	$0	32,000	32000
vertex_ai/meta/llama-3.2-90b-vision-instruct-maas	$0	$0	128,000	2048
vertex_ai/mistral-large@latest	$2	$6	128,000	8191
vertex_ai/mistral-large@2407	$2	$6	128,000	8191
vertex_ai/mistral-nemo@latest	$0.15	$0.15	128,000	128000
vertex_ai/jamba-1.5-mini@001	$0.2	$0.4	256,000	256000
vertex_ai/jamba-1.5-large@001	$2	$8	256,000	256000
vertex_ai/jamba-1.5	$0.2	$0.4	256,000	256000
vertex_ai/jamba-1.5-mini	$0.2	$0.4	256,000	256000
vertex_ai/jamba-1.5-large	$2	$8	256,000	256000
vertex_ai/mistral-nemo@2407	$3	$3	128,000	128000
vertex_ai/codestral@latest	$0.2	$0.6	128,000	128000
vertex_ai/codestral@2405	$0.2	$0.6	128,000	128000
vertex_ai/imagegeneration@006	–	–	nan	nan
vertex_ai/imagen-3.0-generate-001	–	–	nan	nan
vertex_ai/imagen-3.0-fast-generate-001	–	–	nan	nan
text-embedding-004	$0.1	$0	2,048	nan
text-multilingual-embedding-002	$0.1	$0	2,048	nan
textembedding-gecko	$0.1	$0	3,072	nan
textembedding-gecko-multilingual	$0.1	$0	3,072	nan
textembedding-gecko-multilingual@001	$0.1	$0	3,072	nan
textembedding-gecko@001	$0.1	$0	3,072	nan
textembedding-gecko@003	$0.1	$0	3,072	nan
text-embedding-preview-0409	$0.01	$0	3,072	nan
text-multilingual-embedding-preview-0409	$0.01	$0	3,072	nan
palm/chat-bison	$0.12	$0.12	8,192	4096
palm/chat-bison-001	$0.12	$0.12	8,192	4096
palm/text-bison	$0.12	$0.12	8,192	1024
palm/text-bison-001	$0.12	$0.12	8,192	1024
palm/text-bison-safety-off	$0.12	$0.12	8,192	1024
palm/text-bison-safety-recitation-off	$0.12	$0.12	8,192	1024
gemini/gemini-1.5-flash-002	$0.08	$0.3	1,048,576	8192
gemini/gemini-1.5-flash-001	$0.08	$0.3	1,048,576	8192
gemini/gemini-1.5-flash	$0.08	$0.3	1,048,576	8192
gemini/gemini-1.5-flash-latest	$0.08	$0.3	1,048,576	8192
gemini/gemini-1.5-flash-8b-exp-0924	$0	$0	1,048,576	8192
gemini/gemini-1.5-flash-exp-0827	$0	$0	1,048,576	8192
gemini/gemini-1.5-flash-8b-exp-0827	$0	$0	1,000,000	8192
gemini/gemini-pro	$0.35	$1.05	32,760	8192
gemini/gemini-1.5-pro	$3.5	$10.5	2,097,152	8192
gemini/gemini-1.5-pro-002	$3.5	$10.5	2,097,152	8192
gemini/gemini-1.5-pro-001	$3.5	$10.5	2,097,152	8192
gemini/gemini-1.5-pro-exp-0801	$3.5	$10.5	2,097,152	8192
gemini/gemini-1.5-pro-exp-0827	$0	$0	2,097,152	8192
gemini/gemini-1.5-pro-latest	$3.5	$1.05	1,048,576	8192
gemini/gemini-pro-vision	$0.35	$1.05	30,720	2048
gemini/gemini-gemma-2-27b-it	$0.35	$1.05	nan	8192
gemini/gemini-gemma-2-9b-it	$0.35	$1.05	nan	8192
command-r	$0.15	$0.6	128,000	4096
command-r-08-2024	$0.15	$0.6	128,000	4096
command-light	$0.3	$0.6	4,096	4096
command-r-plus	$2.5	$10	128,000	4096
command-r-plus-08-2024	$2.5	$10	128,000	4096
command-nightly	$1	$2	4,096	4096
command	$1	$2	4,096	4096
rerank-english-v3.0	$0	$0	4,096	4096
rerank-multilingual-v3.0	$0	$0	4,096	4096
rerank-english-v2.0	$0	$0	4,096	4096
rerank-multilingual-v2.0	$0	$0	4,096	4096
embed-english-v3.0	$0.1	$0	1,024	nan
embed-english-light-v3.0	$0.1	$0	1,024	nan
embed-multilingual-v3.0	$0.1	$0	1,024	nan
embed-english-v2.0	$0.1	$0	4,096	nan
embed-english-light-v2.0	$0.1	$0	1,024	nan
embed-multilingual-v2.0	$0.1	$0	768	nan
replicate/meta/llama-2-13b	$0.1	$0.5	4,096	4096
replicate/meta/llama-2-13b-chat	$0.1	$0.5	4,096	4096
replicate/meta/llama-2-70b	$0.65	$2.75	4,096	4096
replicate/meta/llama-2-70b-chat	$0.65	$2.75	4,096	4096
replicate/meta/llama-2-7b	$0.05	$0.25	4,096	4096
replicate/meta/llama-2-7b-chat	$0.05	$0.25	4,096	4096
replicate/meta/llama-3-70b	$0.65	$2.75	8,192	8192
replicate/meta/llama-3-70b-instruct	$0.65	$2.75	8,192	8192
replicate/meta/llama-3-8b	$0.05	$0.25	8,086	8086
replicate/meta/llama-3-8b-instruct	$0.05	$0.25	8,086	8086
replicate/mistralai/mistral-7b-v0.1	$0.05	$0.25	4,096	4096
replicate/mistralai/mistral-7b-instruct-v0.2	$0.05	$0.25	4,096	4096
replicate/mistralai/mixtral-8x7b-instruct-v0.1	$0.3	$1	4,096	4096
openrouter/deepseek/deepseek-coder	$0.14	$0.28	66,000	4096
openrouter/microsoft/wizardlm-2-8x22b:nitro	$1	$1	n

README 内容过长，已截取前 64 KB。完整内容请前往 GitHub 仓库查看。