This is a snapshot of the popular LLMs that are available on the Hatz AI platform. Please note that the context window and max output token limits are approximate and not always accurate, depending on the type of request and other factors.
Company | Model | Reasoning?Check out our "Reasoning Models" article | Vision | Input Tokens / Words*** | Output Tokens / Words | Knowledge Cutoff Date |
|
OpenAI | GPT 3.5 Turbo |
|
| 16K / 12K | 4K / 3K | August 2021 |
|
OpenAI | GPT 4 |
|
| 8K / 6K | 8K / 6K | November 2023 |
|
OpenAI | GPT 4o |
| Yes | 128K / 96K | 16K / 12K | September 2023 |
|
OpenAI | o1 | Yes |
| 200K / 150K | 100K / 75K | September 2023 |
|
OpenAI | o3-mini | Yes |
| 200K / 150K | 100K / 75K | September 2023 |
|
OpenAI | GPT 4.5 Preview |
| Yes | 128K / 96K | 16K / 12K | December 2023 |
|
OpenAI | GPT-4.1 |
| Yes | 100K / 75K | 32K / 24K | May 2024 |
|
OpenAI | GPT-4.1 Mini |
| Yes | 100K / 75K | 32K / 24K | May 2024 |
|
OpenAI | GPT-4.1 Nano |
| Yes | 100K / 75K | 32K / 24K | May 2024 |
|
Anthropic | Claude 3 Sonnet |
|
| 200K / 150K | 4K / 3K | August 2023 |
|
Anthropic | Claude 3 Haiku |
|
| 200K / 150K | 4K / 3K | August 2023 |
|
Anthropic | Claude 3.5 Sonnet v2 |
| Yes | 200K / 150K | 8K / 6K | April 2024 |
|
Anthropic | Claude 3.7 Sonnet | Yes (hybrid) | Yes | 200K / 150K | 8K / 6K | October 2024 |
|
xAI | Grok 2 | Yes |
| 132K / 97K | 132K / 97K | July 2024 |
|
xAI | Grok 2 Vision | Yes | Yes | 132K / 97K | 132K / 97K | July 2024 |
|
xAI | Grok 3 | Yes |
| 132K / 97K | 16K / 12K | February 2025 |
|
xAI | Grok 3 Fast | Yes |
| 132K / 97K | 16K / 12K | February 2025 |
|
xAI | Grok 3 Mini | Yes |
| 132K / 97K | 16K / 12K | February 2025 |
|
xAI | Grok 3 Mini Fast | Yes |
| 132K / 97K | 16K / 12K | February 2025 |
|
Gemini 1.5 Flash |
| Yes
| 1 Million / 750K | 8K / 6K | November 2023 |
| |
Gemini 1.5 Pro |
| Yes | 2 Million / 1.5 Million | 8K / 6K | November 2023 |
| |
Gemini 2.0 Flash |
| Yes | 1 Million / 750K | 8K / 6K | June 2024 |
| |
Gemini 2.0 Flash Lite |
| Yes | 1 Million / 750K | 8K / 6K | June 2024 |
| |
MistralAI | Mistral Large |
|
| 32K / 24K | 4K / 3K | October 2023 |
|
MistralAI | Mistral 7B Instruct |
|
|
|
|
|
|
Mistral AI | Mistral 8x7B Instruct |
|
|
|
|
|
|
DeepSeek | DeepSeek R1 | Yes | Yes | 32K / 24K | 32K / 24K | July 2024 |
|
Meta | Llama 3.2 1B Instruct |
|
|
|
|
|
|
Meta | Llama 3.2 11B Instruct |
| Yes |
|
|
|
|
Meta | Llama 3.2 70B Instruct |
|
|
|
|
|
|
Meta | Llama 3.2 8B Instruct |
|
|
|
|
|
|
Amazon | Nova Micro | Yes |
| 128K / 96K | 5K / 3K | Purposefully not disclosed by Amazon |
|
Amazon | Nova Lite | Yes | Yes | 300K / 225K | 5K / 3K | Purposefully not disclosed by Amazon |
|
Amazon | Nova Pro | Yes | Yes | 300K / 225K | 5K / 3K | Purposefully not disclosed by Amazon |
|
***In some cases, tokens are not just words. If you upload a PDF with images, tokens will applied to interpret the images in addition to the words. If you upload a PNG or JPG with no words, tokens will still be used to understand the image.
Use Cases by Company
OpenAI | Sentiment Analysis Content Generation Process Automation |
Anthropic | RFP Responses Content Generation Coding |
xAI | Reasoning |
Analyzing large documents Summarizing reports | |
Mistral | Translating Trained with non-English data |
Meta | Customer Support Small, short tasks |
DeepSeek | Reasoning |
Token
The smallest unit of data that an LLM processes
Usually about 3/4 of a word
If you want to see how many INPUT tokens something is, use this site (it works best for OpenAI models):
***In some cases, tokens are not just words. If you upload a PDF with images, tokens will applied to interpret the images in addition to the words. If you upload a PNG or JPG with no words, tokens will still be used to understand the image.
Context Window
The segment of text that an AI model considers at any given moment when processing or generating language
You can think of this as the size of the input
If you upload a file (PDF, PNG, XLSX, etc) that is below the 30MB limit, but it is larger than the context window for the selected LLM, the request will fail. Try switching to a larger model, like Gemini
Knowledge Cutoff Date
The date that the LLM stopped "learning" new information. If you ask GPT 3.5 Turbo about an event that happened yesterday, it will not have that data
Reasoning
Reasoning models are a type of AI model that are trained to engage in "thinking" before providing an answer, breaking down problems into steps and showing their reasoning process, unlike models that directly generate answers.
They can take more time to answer because they are reflecting on their analysis step-by-step.
Vision
Computer vision gives LLMs the ability to "see" and interpret visual data like images and videos, enabling them to identify objects, classify scenes, and perform tasks that mimic human vision.
On Hatz AI, if you see this image:
next to an AI Model in the model selector, then you can upload image files like JPGs and PNGs.
More Info
To dive deeper into these LLMs, check out these resources*
*Some features outlined on these sites might not be available on the Hatz AI platform, or they might work differently than explained here. Use these articles to better understand the token limits, reasoning models, and use cases.