LLM成本计算器
ChatGPT 和其他 LLM API 定价计算器
计算方式
Tokens
Words
Characters
供应商 | 模型 | 上下文 | 输入/1k Tokens | 输出/1k Tokens | 每次调用 | 总计 | |
---|---|---|---|---|---|---|---|
国内模型 | |||||||
通义千问 | qwen-max-1201 | 0.12 | 0.12 | 0.2400 | 24.00 | ||
通义千问 | qwen-max-0403 | 0.04 | 0.12 | 0.1600 | 16.00 | ||
通义千问 | qwen-max-longcontext | 0.04 | 0.12 | 0.1600 | 16.00 | ||
通义千问 | qwen-max | 0.04 | 0.12 | 0.1600 | 16.00 | ||
通义千问 | qwen-max-0428 | 0.04 | 0.12 | 0.1600 | 16.00 | ||
通义千问 | qwen-max-0107 | 0.04 | 0.12 | 0.1600 | 16.00 | ||
通义千问 | qwen-turbo | 0.002 | 0.006 | 0.0080 | 0.80 | ||
通义千问 | Qwen-Long | 0.0005 | 0.002 | 0.0025 | 0.25 | ||
通义千问 | qwen-plus | 0.004 | 0.0012 | 0.0052 | 0.52 | ||
百度智能云 | ERNIE 4.0 | 0.12 | 0.12 | 0.2400 | 24.00 | ||
百度智能云 | ERNIE-3.5-8K-0205 | 8K | 0.024 | 0.048 | 0.0720 | 7.20 | |
百度智能云 | ERNIE 3.5系列(不含8k-0205版本) | 0.012 | 0.012 | 0.0240 | 2.40 | ||
百度智能云 | ERNIE-Lite-8K-0922 | 0.008 | 0.008 | 0.0160 | 1.60 | ||
百度智能云 | ERNIE-Character-8K | 8K | 0.004 | 0.008 | 0.0120 | 1.20 | |
百度智能云 | ERNIE Speed-AppBuilder | 0.004 | 0.008 | 0.0120 | 1.20 | ||
百度智能云 | ERNIE-Function-8K | 8k | 0.004 | 0.008 | 0.0120 | 1.20 | |
百度智能云 | ERNIE-Tiny-8k | 8k | 0.001 | 0.001 | 0.0020 | 0.20 | |
百川智能 | Baichuan2-Turbo-192k | 192k | 0.016 | 0.016 | 0.0320 | 3.20 | |
百川智能 | Baichuan-NPC-Turbo | 0.015 | 0.015 | 0.0300 | 3.00 | ||
百川智能 | Baichuan2-53B | 0.01 | 0.01 | 0.0200 | 2.00 | ||
百川智能 | Baichuan-NPC-Lite | 0.0099 | 0.0099 | 0.0198 | 1.98 | ||
百川智能 | Baichuan2-Turbo | 0.008 | 0.008 | 0.0160 | 1.60 | ||
百川智能 | Baichuan-Text-Embedding | 0.0005 | 0.0005 | 0.0010 | 0.10 | ||
智谱AI | GLM-4-0520 | 0.1 | 0.1 | 0.2000 | 20.00 | ||
智谱AI | GLM-4 | 0.1 | 0.1 | 0.2000 | 20.00 | ||
智谱AI | GLM-4V | 0.05 | 0.05 | 0.1000 | 10.00 | ||
智谱AI | GLM-4-Airx | 0.01 | 0.01 | 0.0200 | 2.00 | ||
智谱AI | GLM-4-Air | 0.001 | 0.001 | 0.0020 | 0.20 | ||
智谱AI | GLM-3-Turbo | 0.001 | 0.001 | 0.0020 | 0.20 | ||
MiniMax开放平台 | ChatCompletion V2 abab6 | 0.1 | 0.1 | 0.2000 | 20.00 | ||
MiniMax开放平台 | ChatCompletion V2 abab6.5 | 0.03 | 0.03 | 0.0600 | 6.00 | ||
MiniMax开放平台 | ChatCompletion V2 abab5.5 | 0.015 | 0.015 | 0.0300 | 3.00 | ||
MiniMax开放平台 | ChatCompletion V2 abab6.5s | 0.01 | 0.01 | 0.0200 | 2.00 | ||
MiniMax开放平台 | ChatCompletion V2 abab6.5g | 0.005 | 0.005 | 0.0100 | 1.00 | ||
MiniMax开放平台 | ChatCompletion V2 abab5.5s | 0.005 | 0.005 | 0.0100 | 1.00 | ||
腾讯云 | 混元-pro | 0.03 | 0.1 | 0.1300 | 13.00 | ||
腾讯云 | 混元-standard | 0.0045 | 0.005 | 0.0095 | 0.95 | ||
Moonshot AI | moonshot-v1-128k | 128k | 0.06 | 0.06 | 0.1200 | 12.00 | |
Moonshot AI | Mistral-Medium | 0.027 | 0.081 | 0.1080 | 10.80 | ||
Moonshot AI | moonshot-v1-32k | 32k | 0.024 | 0.024 | 0.0480 | 4.80 | |
Moonshot AI | moonshot-v1-8k | 8k | 0.012 | 0.012 | 0.0240 | 2.40 | |
火山引擎 | Skylark2-pro-32k | 32k | 0.012 | 0.036 | 0.0480 | 4.80 | |
火山引擎 | Skylark2-pro-4k | 4k | 0.011 | 0.015 | 0.0260 | 2.60 | |
火山引擎 | Skylark2-pro-character-4k | 4k | 0.011 | 0.015 | 0.0260 | 2.60 | |
火山引擎 | Skylark2-pro-turbo-8k | 8k | 0.004 | 0.011 | 0.0150 | 1.50 | |
火山引擎 | Doubao-pro-128k | 128k | 0.005 | 0.009 | 0.0140 | 1.40 | |
火山引擎 | Skylark2-lite-8k | 8k | 0.004 | 0.004 | 0.0080 | 0.80 | |
火山引擎 | Doubao-pro-32k | 32k | 0.0008 | 0.002 | 0.0028 | 0.28 | |
火山引擎 | Doubao-pro-4k | 4k | 0.0008 | 0.002 | 0.0028 | 0.28 | |
火山引擎 | Doubao-lite-128k | 128k | 0.0008 | 0.001 | 0.0018 | 0.18 | |
火山引擎 | Doubao-lite-32k | 32k | 0.0003 | 0.0006 | 0.0009 | 0.09 | |
火山引擎 | Doubao-lite-4k | 4k | 0.0003 | 0.0006 | 0.0009 | 0.09 | |
讯飞星火 | 星火大模型V3.5 | 0.033 | 0.033 | 0.0660 | 6.60 | ||
讯飞星火 | 星火大模型V3.0 | 0.03 | 0.03 | 0.0600 | 6.00 | ||
讯飞星火 | 星火大模型V1.5 | 0.015 | 0.015 | 0.0300 | 3.00 | ||
零一万物 | yi-34b-chat-200k | 200k | 0.012 | 0.012 | 0.0240 | 2.40 | |
零一万物 | yi-vl-plus | 0.006 | 0.006 | 0.0120 | 1.20 | ||
零一万物 | yi-34b-chat-0205 | 0.0025 | 0.0025 | 0.0050 | 0.50 | ||
DeepSeek | DeepSeek-V2 | 32K | 0.001 | 0.002 | 0.0030 | 0.30 | |
Chat/Completion | |||||||
OpenAI | gpt-4o-mini | 128K | 0.00015 | 0.0006 | 0.0007 | 0.07 | |
OpenAI | gpt-4o | 128K | 0.005 | 0.015 | 0.0200 | 2.00 | |
OpenAI | gpt-3.5-turbo | 0.003 | 0.006 | 0.0090 | 0.90 | ||
OpenAI | gpt-3.5-turbo-0125 | 16K | 0.0005 | 0.0015 | 0.0020 | 0.20 | |
OpenAI | gpt-4-turbo | 128K | 0.01 | 0.03 | 0.0400 | 4.00 | |
OpenAI | gpt-4 | 8K | 0.03 | 0.06 | 0.0900 | 9.00 | |
OpenAI | gpt-3.5-turbo-instruct | 4K | 0.0015 | 0.002 | 0.0035 | 0.35 | |
OpenAI | gpt-4o-mini-2024-07-18 | 128K | 0.00015 | 0.0006 | 0.0007 | 0.07 | |
OpenAI | gpt-4-turbo-2024-04-09 | 128K | 0.01 | 0.03 | 0.0400 | 4.00 | |
OpenAI | gpt-4-32k | 32K | 0.06 | 0.12 | 0.1800 | 18.00 | |
OpenAI | gpt-4-0125-preview | 128K | 0.01 | 0.03 | 0.0400 | 4.00 | |
OpenAI | gpt-4-1106-preview | 128K | 0.01 | 0.03 | 0.0400 | 4.00 | |
OpenAI | gpt-4-vision-preview | 128K | 0.01 | 0.03 | 0.0400 | 4.00 | |
OpenAI | gpt-3.5-turbo-1106 | 4K | 0.001 | 0.002 | 0.0030 | 0.30 | |
OpenAI | gpt-3.5-turbo-0613 | 4K | 0.0015 | 0.002 | 0.0035 | 0.35 | |
OpenAI | gpt-3.5-turbo-16k-0613 | 4K | 0.003 | 0.004 | 0.0070 | 0.70 | |
OpenAI | gpt-3.5-turbo-0301 | 4K | 0.0015 | 0.002 | 0.0035 | 0.35 | |
OpenAI | davinci-002 | 4K | 0.002 | 0.002 | 0.0040 | 0.40 | |
OpenAI | babbage-002 | 4K | 0.0004 | 0.0004 | 0.0008 | 0.08 | |
Anthropic | claude-3-opus | 200K | 0.015 | 0.075 | 0.0900 | 9.00 | |
Anthropic | claude-3-sonnet | 200K | 0.003 | 0.015 | 0.0180 | 1.80 | |
Anthropic | claude-3-haiku | 200K | 0.00025 | 0.00125 | 0.0015 | 0.15 | |
Anthropic | claude-2.1 | 200K | 0.008 | 0.024 | 0.0320 | 3.20 | |
Anthropic | claude-2.0 | 100K | 0.008 | 0.024 | 0.0320 | 3.20 | |
Anthropic | claude-instant-1.2 | 100K | 0.0008 | 0.0024 | 0.0032 | 0.32 | |
Deepinfra | llama-3-70b-instruct | 8K | 0.00059 | 0.00079 | 0.0014 | 0.14 | |
Deepinfra | llama-3-8b-instruct | 8K | 0.0001 | 0.0001 | 0.0002 | 0.02 | |
gemini-pro | 32K | 0.00013 | 0.00038 | 0.0005 | 0.05 | ||
gemini-1.5-pro | 1M | 0.007 | 0.021 | 0.0280 | 2.80 | ||
gemini-flash-1.5 | 2.8M | 0.000075 | 0.0003 | 0.0004 | 0.04 | ||
Deepinfra | gemma-7b-it | 8K | 0.0001 | 0.0001 | 0.0002 | 0.02 | |
Mistral | mistral-large | 32K | 0.008 | 0.024 | 0.0320 | 3.20 | |
Mistral | mistral-medium | 32K | 0.0027 | 0.081 | 0.0837 | 8.37 | |
Mistral | mistral-small | 32K | 0.002 | 0.006 | 0.0080 | 0.80 | |
Mistral | mixtral-8x7b | 32K | 0.0007 | 0.0007 | 0.0014 | 0.14 | |
Mistral | mistral-7b | 32K | 0.00025 | 0.00025 | 0.0005 | 0.05 | |
Cohere | command-r-plus | 128K | 0.003 | 0.015 | 0.0180 | 1.80 | |
Cohere | command-r | 4K | 0.0005 | 0.0015 | 0.0020 | 0.20 | |
Cohere | command | 4K | 0.0003 | 0.0006 | 0.0009 | 0.09 | |
Perplexity | pplx-70b-online | 4K | 0.0001 | 0.0001 | 0.0002 | 0.02 | |
Perplexity | pplx-7b-online | 4K | 0.0002 | 0.0002 | 0.0004 | 0.04 | |
OpenChat | openchat-7b | 8K | 0.00013 | 0.00013 | 0.0003 | 0.03 | |
Groq | llama-3-70b | 8K | 0.00059 | 0.00079 | 0.0014 | 0.14 | |
Groq | llama-3-8b | 8K | 0.00005 | 0.0001 | 0.0002 | 0.02 | |
Groq | llama-2-70b | 4K | 0.00064 | 0.0008 | 0.0014 | 0.14 | |
Groq | llama-2-7b | 2K | 0.0001 | 0.0001 | 0.0002 | 0.02 | |
Groq | mixtral-8x7b | 32K | 0.00027 | 0.00027 | 0.0005 | 0.05 | |
Groq | gemma-7b | 8K | 0.0001 | 0.0001 | 0.0002 | 0.02 | |
Cloudflare | llama-2-7b-chat-fp16 | 3K | 0.00056 | 0.00066 | 0.0012 | 0.12 | |
Cloudflare | llama-2-7b-chat-int8 | 2K | 0.00016 | 0.00024 | 0.0004 | 0.04 | |
Cloudflare | mistral-7b-instruct | 32K | 0.00011 | 0.00019 | 0.0003 | 0.03 | |
Lynn | llama-3-soliloquy-8b | 24K | 0.0001 | 0.0001 | 0.0002 | 0.02 | |
Replicate | meta-llama-3-70b-instruct | 8K | 0.00065 | 0.00275 | 0.0034 | 0.34 | |
Replicate | meta-llama-3-8b-instruct | 8K | 0.00005 | 0.00025 | 0.0003 | 0.03 | |
Replicate | llama-2-13b | 4K | 0.0001 | 0.0005 | 0.0006 | 0.06 | |
Replicate | llama-2-7b | 4K | 0.00005 | 0.00025 | 0.0003 | 0.03 | |
Replicate | llama-2-70b | 4K | 0.00065 | 0.00275 | 0.0034 | 0.34 | |
Replicate | mistral-7b-v0.1 | 32K | 0.00005 | 0.00025 | 0.0003 | 0.03 | |
Replicate | mistral-7b-instruct-v0.2 | 32K | 0.00005 | 0.00025 | 0.0003 | 0.03 | |
Replicate | mixtral-8x7b-instruct-v0.1 | 32K | 0.0003 | 0.001 | 0.0013 | 0.13 | |
AWS | jurassic-2-ultra | 32K | 0.0188 | 0.0188 | 0.0376 | 3.76 | |
AWS | jurassic-2-mid | 32K | 0.0125 | 0.0125 | 0.0250 | 2.50 | |
AWS | titan-text-lite | 32K | 0.0003 | 0.0004 | 0.0007 | 0.07 | |
AWS | titan-text-express | 32K | 0.0008 | 0.0016 | 0.0024 | 0.24 | |
AWS | claude-instant | 32K | 0.0008 | 0.0024 | 0.0032 | 0.32 | |
AWS | claude-3-sonnet | 32K | 0.003 | 0.015 | 0.0180 | 1.80 | |
AWS | claude-3-haiku | 32K | 0.00025 | 0.00125 | 0.0015 | 0.15 | |
AWS | command | 32K | 0.0015 | 0.002 | 0.0035 | 0.35 | |
AWS | command-light | 32K | 0.0003 | 0.0006 | 0.0009 | 0.09 | |
AWS | llama-2-chat-13b | 32K | 0.00075 | 0.001 | 0.0018 | 0.18 | |
AWS | llama-2-chat-70b | 32K | 0.00195 | 0.00256 | 0.0045 | 0.45 | |
AWS | mistral-7b | 32K | 0.00015 | 0.0002 | 0.0003 | 0.03 | |
AWS | mistral-8x7b | 32K | 0.00045 | 0.0007 | 0.0011 | 0.11 | |
Fine/tuning | |||||||
OpenAI | GPT-3.5 Turbo | 4K | 0.012 | 0.016 | 0.0280 | 2.80 | |
PaLM 2 | 8K | 0.002 | 0.002 | 0.0040 | 0.40 | ||
Embedding | |||||||
Titan | Titan Embeddings | 0.0001 | 0.0001 | 0.01 | |||
OpenAI | Ada v2 | 0.0001 | 0.0001 | 0.01 | |||
PaLM 2 | 0.0004 | 0.0004 | 0.04 | ||||
Cohere | Embed | 0.0004 | 0.0004 | 0.04 |