OpenAI LLM Model
(Redirected from OpenAI LLM model)
Jump to navigation
Jump to search
A OpenAI LLM Model is a large neural autoregressive language model that is an OpenAI Model.
- Context:
- It can range from being a OpenAI Pure LLM Model to being a OpenAI Chat Model.
- ...
- Example(s):
- a GPT-3 Model, such as: text-davinci-002.
- a GPT-3.5 Model, such as: text-davinci-003.
- a GPT-4 Model, such as: gpt-4-32k.
- ...
- Counter-Example(s):
- See: Decoder-only Transformer-based LLM.
References
2024-09-20
- LLM
| Model | Input Tokens Cost | Output Tokens Cost | Context Window | Output Limit | Focus |
|---|---|---|---|---|---|
| o1-preview | $15 per million (3x) | $60 per million (4x) | 128k | 32k (7.8x) | Advanced reasoning, complex problem-solving |
| o1-mini | $3 per million (0.6x) | $12 per million (0.8x) | 128k | 64k (15.6x) | Speed and efficiency, focused reasoning |
| GPT-4o | $5 per million (1x) | $15 per million (1x) | 128k | 4,096 (1x) | Multimodal reasoning (text, vision, audio) |
| GPT-4o mini | $0.15 per million (0.03x) | $0.60 per million (0.04x) | 128k | 16,384 (4x) | Cost-efficient, fast reasoning, coding |
2023
- Python
model_lst = openai.Model.list()
for model in filtered_model_data:
print('{:25s} {:15s} {:20s}'.format(model['id'], datetime.fromtimestamp(model['created']).strftime("%Y-%m-%d"), model['owned_by']))
Model ID Created Date Model Name ada 2022-04-07 openai babbage 2022-04-07 openai davinci 2022-04-07 openai curie 2022-04-07 openai curie-instruct-beta 2022-04-07 openai davinci-instruct-beta 2022-04-07 openai text-davinci-001 2022-04-07 openai text-ada-001 2022-04-07 openai text-babbage-001 2022-04-07 openai text-curie-001 2022-04-07 openai text-davinci-edit-001 2022-04-13 openai code-davinci-edit-001 2022-04-13 openai text-davinci-002 2022-04-13 openai gpt-3.5-turbo 2023-02-28 openai gpt-3.5-turbo-0301 2023-03-01 openai gpt-3.5-turbo-16k-0613 2023-05-30 openai gpt-3.5-turbo-0613 2023-06-12 openai gpt-4-0613 2023-06-12 openai gpt-4-0314 2023-06-27 openai gpt-4 2023-06-27 openai
2023
- https://platform.openai.com/docs/models/
- QUOTE: The OpenAI API is powered by a diverse set of models with different capabilities and price points. You can also make limited customizations to our original base models for your specific use case with fine-tuning.
| Latest model | Description | Max tokens | Training data |
|---|---|---|---|
| gpt-4 | More capable than any GPT-3.5 model, able to do more complex tasks, and optimized for chat. Will be updated with our latest model iteration. | 8,192 tokens | Up to Sep 2021 |
| gpt-4-0314 | Snapshot of gpt-4 from March 14th 2023. Unlike gpt-4, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.
|
8,192 tokens | Up to Sep 2021 |
| gpt-4-32k | Same capabilities as the base gpt-4 mode but with 4x the context length. Will be updated with our latest model iteration.
|
32,768 tokens | Up to Sep 2021 |
| gpt-4-32k-0314 | Snapshot of gpt-4-32 from March 14th 2023. Unlike gpt-4-32k, this model will not receive updates, and will only be supported for a three month period ending on June 14th 2023.
|
32,768 tokens | Up to Sep 2021 |
2023
- Pascale Fung. (2023). “ChatGPT: What It Can and Cannot Do?." Presentation
.
