openai/chatgpt的api接口,各个模型的最大输入token一览表

chatgpt的各个3.5api模型接口的最大输入量一览表:

MODEL DESCRIPTION CONTEXT WINDOW TRAINING DATA
gpt-3.5-turbo-1106 Updated GPT 3.5 Turbo

New


The latest GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens. 
16,385 tokens Up to Sep 2021
gpt-3.5-turbo Currently points to gpt-3.5-turbo-0613. Will point to gpt-3.5-turbo-1106 starting Dec 11, 2023.  4,096 tokens Up to Sep 2021
gpt-3.5-turbo-16k Currently points to gpt-3.5-turbo-0613. Will point to gpt-3.5-turbo-1106 starting Dec 11, 2023.  16,385 tokens Up to Sep 2021
gpt-3.5-turbo-instruct Similar capabilities as text-davinci-003 but compatible with legacy Completions endpoint and not Chat Completions. 4,096 tokens Up to Sep 2021
gpt-3.5-turbo-0613

Legacy

Snapshot of gpt-3.5-turbo from June 13th 2023. Will be deprecatedon June 13, 2024. 4,096 tokens Up to Sep 2021
gpt-3.5-turbo-16k-0613

Legacy

Snapshot of gpt-3.5-16k-turbo from June 13th 2023. Will be deprecated on June 13, 2024. 16,385 tokens Up to Sep 2021
gpt-3.5-turbo-0301

Legacy

Snapshot of gpt-3.5-turbo from March 1st 2023. Will be deprecated on June 13th 2024. 4,096 tokens Up to Sep 2021
text-davinci-003

Legacy

Can do language tasks with better quality and consistency than the curie, babbage, or ada models. Will be deprecated on Jan 4th 2024. 4,096 tokens Up to Jun 2021
text-davinci-002

Legacy

Similar capabilities to text-davinci-003 but trained with supervised fine-tuning instead of reinforcement learning. Will be deprecated on Jan 4th 2024. 4,096 tokens Up to Jun 2021
code-davinci-002

Legacy

Optimized for code-completion tasks. Will be deprecated on Jan 4th 2024. 8,001 tokens Up to Jun 2021

chatgpt的各个4.0api模型接口的最大输入量一览表:

MODEL DESCRIPTION CONTEXT WINDOW TRAINING DATA
gpt-4-1106-preview GPT-4 Turbo

New


The latest GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Returns a maximum of 4,096 output tokens. This preview model is not yet suited for production traffic. Learn more.
128,000 tokens Up to Apr 2023
gpt-4-vision-preview GPT-4 Turbo with vision

New


Ability to understand images, in addition to all other GPT-4 Turbo capabilties. Returns a maximum of 4,096 output tokens. This is a preview model version and not suited yet for production traffic. Learn more.
128,000 tokens Up to Apr 2023
gpt-4 Currently points to gpt-4-0613. See continuous model upgrades. 8,192 tokens Up to Sep 2021
gpt-4-32k Currently points to gpt-4-32k-0613. See continuous model upgrades. 32,768 tokens Up to Sep 2021
gpt-4-0613 Snapshot of gpt-4 from June 13th 2023 with improved function calling support. 8,192 tokens Up to Sep 2021
gpt-4-32k-0613 Snapshot of gpt-4-32k from June 13th 2023 with improved function calling support. 32,768 tokens Up to Sep 2021
gpt-4-0314

Legacy

Snapshot of gpt-4 from March 14th 2023 with function calling support. This model version will be deprecated on June 13th 2024. 8,192 tokens Up to Sep 2021
gpt-4-32k-0314

Legacy

Snapshot of gpt-4-32k from March 14th 2023 with function calling support. This model version will be deprecated on June 13th 2024. 32,768 tokens Up to Sep 2021

 

你可能感兴趣的:(chatgpt,人工智能)