Question: How can I switch among the gpt 5.5 models?

API
1

Hi everyone.

Background

I would like to process a total of 14 M tokens, so I am planning to use the Batch API.
According to the limits page on the dashboard, gpt-5.5-long-context allows up to 5,000,000 TPD (Tokens Per Day).
Therefore, I want to specify the gpt-5.5-long-context model when creating the JSONL file to define the batch requests.

Issue

I checked the available models using the client.models.list() method as described in the documentation.

Here is my minimal reproducible code:

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()
client = OpenAI()

available_models = client.models.list()
for model in available_models:
    print(model.id)

The output is as follows:

text-embedding-ada-002
whisper-1
gpt-3.5-turbo
tts-1
gpt-3.5-turbo-16k
gpt-4-0613
gpt-4
davinci-002
babbage-002
gpt-3.5-turbo-instruct
gpt-3.5-turbo-instruct-0914
gpt-3.5-turbo-1106
tts-1-hd
tts-1-1106
tts-1-hd-1106
text-embedding-3-small
text-embedding-3-large
gpt-3.5-turbo-0125
gpt-4-turbo
gpt-4-turbo-2024-04-09
gpt-4o
gpt-4o-2024-05-13
gpt-4o-mini-2024-07-18
gpt-4o-mini
gpt-4o-2024-08-06
omni-moderation-latest
omni-moderation-2024-09-26
o1-2024-12-17
o1
o3-mini
o3-mini-2025-01-31
gpt-4o-2024-11-20
gpt-4o-mini-search-preview-2025-03-11
gpt-4o-mini-search-preview
gpt-4o-transcribe
gpt-4o-mini-transcribe
o1-pro-2025-03-19
o1-pro
gpt-4o-mini-tts
o3-2025-04-16
o4-mini-2025-04-16
o3
o4-mini
gpt-4.1-2025-04-14
gpt-4.1
gpt-4.1-mini-2025-04-14
gpt-4.1-mini
gpt-4.1-nano-2025-04-14
gpt-4.1-nano
gpt-image-1
gpt-4o-transcribe-diarize
gpt-5-chat-latest
gpt-5-2025-08-07
gpt-5
gpt-5-mini-2025-08-07
gpt-5-mini
gpt-5-nano-2025-08-07
gpt-5-nano
gpt-audio-2025-08-28
gpt-realtime
gpt-realtime-2025-08-28
gpt-audio
gpt-5-codex
gpt-image-1-mini
gpt-5-pro-2025-10-06
gpt-5-pro
gpt-audio-mini
gpt-audio-mini-2025-10-06
gpt-5-search-api
gpt-realtime-mini
gpt-realtime-mini-2025-10-06
sora-2
sora-2-pro
gpt-5-search-api-2025-10-14
gpt-5.1-chat-latest
gpt-5.1-2025-11-13
gpt-5.1
gpt-5.1-codex
gpt-5.1-codex-mini
gpt-5.1-codex-max
gpt-image-1.5
gpt-5.2-2025-12-11
gpt-5.2
gpt-5.2-pro-2025-12-11
gpt-5.2-pro
gpt-5.2-chat-latest
gpt-4o-mini-transcribe-2025-12-15
gpt-4o-mini-transcribe-2025-03-20
gpt-4o-mini-tts-2025-03-20
gpt-4o-mini-tts-2025-12-15
gpt-realtime-mini-2025-12-15
gpt-audio-mini-2025-12-15
chatgpt-image-latest
gpt-5.2-codex
gpt-5.3-codex
gpt-realtime-1.5
gpt-audio-1.5
gpt-4o-search-preview
gpt-4o-search-preview-2025-03-11
gpt-5.3-chat-latest
gpt-5.4-2026-03-05
gpt-5.4-pro
gpt-5.4-pro-2026-03-05
gpt-5.4
gpt-5.4-nano-2026-03-17
gpt-5.4-nano
gpt-5.4-mini-2026-03-17
gpt-5.4-mini
gpt-image-2
gpt-image-2-2026-04-21
gpt-5.5
gpt-5.5-2026-04-23
gpt-5.5-pro
gpt-5.5-pro-2026-04-23
chat-latest
gpt-realtime-translate
gpt-realtime-2
gpt-realtime-whisper

As you can see, I could not find the gpt-5.5-long-context model in the response.

Question

  1. Can’t I specify gpt-5.5-long-context model in the JSONL file uploaded for a batch job?
  2. If we cannot use that specific ID, will the server automatically route the request to the long-context variant if we simply pass model="gpt-5.5" with a large prompt, as shown in the example below?
{
  "custom_id": "request-1",
  "method": "POST",
  "url": "/v1/responses",
  "body": {
    "model": "gpt-5.5",
    "messages": [
      {
        "role": "system",
        "content": "SYSTEM_PROMPT"
      },
      {
        "role": "user",
        "content": "LONG_CONTEXT..."
      }
    ],
  }
}
2

There is not a separate model name required.

“Long context” is simply an increased amount of billing per token when you send an input over the previous 272k that models before gpt-5.4 had as an input limit.

Now gpt-5.4 and gpt-5.5 can accept up to 1M context length input, with an automatic switch in pricing when you pass the previous input threshold.

You do not need to pick a special model; you only need to send more input to have your bill for the entire API call increased by 100%/50%.

Reminder, not only do you have a batch input file size limit of 200 MB, but your API organization will also have a token queue limit for the batch endpoint - and the usage of API limits after passing the 272k threshold of input on calls is also doubled, or when indicated a separate model in your limits, halved.

3

Hi @_j .

Thank you for your detailed reply and sincere reminder.
I can now proceed with my project with greater clarity.
Thank you very much!