OpenAI付费账号可以用哪些模型，又有什么限制？

本文目录 隐藏

之前给大家分享了《OpenAI免费账号可以用哪些模型，又有什么限制？》，可以说OpenAI免费账号的可用模型和速率限制还是比较严重的，如果你想取消这些限制（获取更多模型的调用权限），则需要在OpenAI platform绑定支付方式，本文ChatGPT中文网就分享下OpenAI付费账号在使用OpenAI API时可以用哪些模型，又有什么限制。

一、什么是OpenAI付费账号

OpenAI付费账号就是指在OpenAI platform绑定了支付方式并消费了的账号，目前OpenAI platform只支持用国外信用卡绑定，详细教程：

《OpenAI API如何充值余额？给账单添加付款详细信息Add payment details教程》

OpenAI将付费账号分为5个等级（Tier 1 – Tier 5），随着在OpenAI API上的花费增加，OpenAI将自动将账户提升到下一个使用层次，这会增加大多数模型的速率限制，详细的每个层次的要求和限制如下：

层级	要求	金额限制
Tier 1	支付了5美元	$100 / month
Tier 2	支付了50美元并且自首次成功支付后已超过7天	$500 / month
Tier 3	支付了100美元并且自首次成功支付后已超过7天	$1,000 / month
Tier 4	支付了250美元并且自首次成功支付后已超过14天	$5,000 / month
Tier 5	支付了1000美元并且自首次成功支付后已超过30天	$10,000 / month

二、OpenAI付费账号可用模型与限制

跟免费账号一样，OpenAI对于OpenAI付费账号的限制同样包括每分钟令牌数（TPM）、每分钟或每天的请求数（RPM/RPD）以及其他特定于模型的限制，不过针对付费账号，可用模型变多、限制变少，下表就是OpenAI付费账号可用模型与限制（更新于2025年4月，最新的以官网为准）：

Model	Token limits	Request and other limits	Batch queue limits
Chat
gpt-3.5-turbo	200,000 TPM	500 RPM 10,000 RPD	2,000,000 TPD
gpt-3.5-turbo-0125	200,000 TPM	500 RPM 10,000 RPD	2,000,000 TPD
gpt-3.5-turbo-1106	200,000 TPM	500 RPM 10,000 RPD	2,000,000 TPD
gpt-3.5-turbo-16k	200,000 TPM	500 RPM 10,000 RPD	2,000,000 TPD
gpt-3.5-turbo-instruct	90,000 TPM	3,500 RPM	200,000 TPD
gpt-3.5-turbo-instruct-0914	90,000 TPM	3,500 RPM	200,000 TPD
gpt-4.1 Shared limits: gpt-4.1-2025-04-14	30,000 TPM	500 RPM	900,000 TPD
gpt-4.1 (long context)	200,000 TPM	100 RPM	2,000,000 TPD
gpt-4.1-mini Shared limits: gpt-4.1-mini-2025-04-14	200,000 TPM	500 RPM	2,000,000 TPD
gpt-4.1-mini (long context)	400,000 TPM	200 RPM	4,000,000 TPD
gpt-4.1-nano Shared limits: gpt-4.1-nano-2025-04-14	200,000 TPM	500 RPM	2,000,000 TPD
gpt-4.1-nano (long context)	400,000 TPM	200 RPM	4,000,000 TPD
gpt-4.5-preview Shared limits: gpt-4.5-preview-2025-02-27	125,000 TPM	1,000 RPM	50,000 TPD
gpt-4o Shared limits: gpt-4o-2024-05-13 gpt-4o-2024-08-06 gpt-4o-2024-11-20 gpt-4o-audio-preview gpt-4o-audio-preview-2024-10-01 gpt-4o-audio-preview-2024-12-17	30,000 TPM	500 RPM	90,000 TPD
gpt-4o-mini Shared limits: gpt-4o-mini-2024-07-18 gpt-4o-mini-audio-preview gpt-4o-mini-audio-preview-2024-12-17	200,000 TPM	500 RPM 10,000 RPD	2,000,000 TPD
gpt-4o-mini-search-preview	6,000 TPM	100 RPM
gpt-4o-mini-search-preview-2025-03-11	6,000 TPM	100 RPM
gpt-4o-mini-transcribe	50,000 TPM	500 RPM
gpt-4o-search-preview	6,000 TPM	100 RPM
gpt-4o-search-preview-2025-03-11	6,000 TPM	100 RPM
gpt-4o-transcribe	10,000 TPM	500 RPM
Text
babbage-002	250,000 TPM	3,000 RPM
davinci-002	250,000 TPM	3,000 RPM
o1-mini	200,000 TPM	500 RPM	2,000,000 TPD
o1-mini-2024-09-12	200,000 TPM	500 RPM	2,000,000 TPD
o1-preview	30,000 TPM	500 RPM	90,000 TPD
o1-preview-2024-09-12	30,000 TPM	500 RPM	90,000 TPD
text-embedding-3-large	1,000,000 TPM	3,000 RPM	3,000,000 TPD
text-embedding-3-small	1,000,000 TPM	3,000 RPM	3,000,000 TPD
text-embedding-ada-002	1,000,000 TPM	3,000 RPM	3,000,000 TPD
Moderation
omni-moderation-2024-09-26	10,000 TPM	500 RPM 10,000 RPD
omni-moderation-latest	10,000 TPM	500 RPM 10,000 RPD
text-moderation-latest	150,000 TPM	1,000 RPM
text-moderation-stable	150,000 TPM	1,000 RPM
Fine-Tuning Inference (shares limits with base model)
babbage-002	250,000	3,000
davinci-002	250,000	3,000
gpt-3.5-turbo-0125	200,000	500
gpt-3.5-turbo-0613	200,000	500
gpt-3.5-turbo-1106	200,000	500
gpt-4-0613	10,000	500
gpt-4o-2024-05-13	30,000	500
gpt-4o-mini-2024-07-18	200,000	500
Fine-tuning Training	active / queued jobs	jobs per day
babbage-002	3	48
davinci-002	3	48
gpt-3.5-turbo-0613	3	48
Image
dall-e-2		500 RPM 5 images per minute
dall-e-3		500 RPM 5 images per minute
Audio
gpt-4o-mini-tts	50,000 TPM	500 RPM
tts-1		500 RPM
tts-1-1106		500 RPM
tts-1-hd		500 RPM
tts-1-hd-1106		500 RPM
whisper-1		500 RPM
Other
Default limits for all other models	250,000 TPM	3,000 RPM