Text Models (LLM)

Overview

The AI/ML API provides access to text-based models, also known as Large Language Models (LLMs), and allows you to interact with them through natural language (that's why a third common name for such models is chat models). These models can be applied to various tasks, enabling the creation of diverse applications using our API. For example, text models can be used to:

• Create a system that searches your photos using text prompts.

• Act as a psychological supporter.

• Play games with you through natural language.

• Assist you with coding.

• Perform a security assessment (pentests) on servers for vulnerabilities.

• Write documentation for your services.

• Serve as a grammar corrector for multiple languages with deep context understanding.

• And much more.

We support multiple text models. You can find the complete list along with API reference links at the end of the page.

Text Model Specific Capabilities

There are several capabilities of text models that are worth mentioning separately.

Completion allows the model to analyze a given text fragment and predict how it might continue based on the probabilities of the next possible tokens or characters. Chat Completion extends this functionality, enabling a simulated dialogue between the user and the model based on predefined roles (e.g., "strict language teacher" and "student"). A detailed description and examples can be found in our Completion and Chat Completion article.

---

An evolution of chat completion includes Assistants (preconfigured conversational agents with specific roles) and Threads (a mechanism for maintaining conversation history for context). Examples of this functionality can be found in the Managing Assistants & Threads article.

---

Function Calling allows a chat model to invoke external programmatic tools (e.g., a function you have written) while generating a response. A detailed description and examples are available in the Function Calling article.

Quick Code Example

We will call the gpt-4o model using the Python programming language and the OpenAI SDK.

If you need a more detailed explanation of how to call a model's API in code, check out our QUICKSTART section.

%pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.aimlapi.com/v1",

    # Insert your AIML API Key in the quotation marks instead of <YOUR_AIMLAPI_KEY>:
    api_key="<YOUR_AIMLAPI_KEY>",  
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "system",
            "content": "You are an AI assistant who knows everything.",
        },
        {
            "role": "user",
            "content": "Tell me, why is the sky blue?"
        },
    ],
)

message = response.choices[0].message.content

print(f"Assistant: {message}")

By running this code example, we received the following response from the chat model:

Assistant: The sky appears blue due to a phenomenon called Rayleigh scattering. When sunlight enters Earth's atmosphere, it collides with gas molecules and small particles. Sunlight is made up of different colors, each with different wavelengths. Blue light has a shorter wavelength and is scattered in all directions by the gas molecules in the atmosphere more than other colors with longer wavelengths, such as red or yellow.
As a result, when you look up at the sky during the day, you see this scattered blue light being dispersed in all directions, making the sky appear blue to our eyes. During sunrise and sunset, the sun's light passes through a greater thickness of Earth's atmosphere, scattering the shorter blue wavelengths out of your line of sight and leaving the longer wavelengths, like red and orange, more dominant, which is why the sky often turns those colors at those times.

All Available Text Models (LLM)

Model ID	Developer	Context	Model Card
gpt-4o	Open AI	128000	Chat GPT-4o
gpt-4o-2024-08-06	Open AI	128000	GPT-4o-2024-08-06
gpt-4o-2024-05-13	Open AI	128000	GPT-4o-2024-05-13
gpt-4o-mini	Open AI	128000	Chat GPT 4o mini
gpt-4o-mini-2024-07-18	Open AI	128000	-
chatgpt-4o-latest	Open AI	128000	-
gpt-4o-audio-preview	Open AI	128000	GPT-4o Audio Preview
gpt-4o-mini-audio-preview	Open AI	128000	GPT-4o mini Audio
gpt-4o-search-preview	Open AI	128000	GPT-4o Search Preview
gpt-4o-mini-search-preview	Open AI	128000	GPT-4o Mini Search Preview
gpt-4-turbo	Open AI	128000	Chat GPT 4 Turbo
gpt-4-turbo-2024-04-09	Open AI	128000	-
gpt-4	Open AI	8000	Chat GPT 4
gpt-4-0125-preview	Open AI	8000	-
gpt-4-1106-preview	Open AI	8000	-
gpt-3.5-turbo	Open AI	16000	Chat GPT 3.5 Turbo
gpt-3.5-turbo-0125	Open AI	16000	Chat GPT-3.5 Turbo 0125
gpt-3.5-turbo-1106	Open AI	16000	Chat GPT-3.5 Turbo 1106
o1	Open AI	200000	OpenAI o1
o1-preview	Open AI	128000	OpenAI o1-preview
o1-preview-2024-09-12	Open AI	128000	-
o1-mini	Open AI	128000	OpenAI o1-mini
o1-mini-2024-09-12	Open AI	128000	-
o3-mini	Open AI	200000	OpenAI o3 mini
gpt-4.5-preview	Open AI	128000	Chat GPT 4.5 preview
openai/gpt-4.1-2025-04-14	Open AI	1000000	Coming Soon
openai/gpt-4.1-mini-2025-04-14	Open AI	1000000	Coming Soon
openai/gpt-4.1-nano-2025-04-14	Open AI	1000000	Coming Soon
DeepSeek V3	DeepSeek	128000	DeepSeek V3
DeepSeek R1	DeepSeek	128000	DeepSeek R1
meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo	Meta	131000	Llama 3.2 90B Vision Instruct Turbo
google/gemma-2-27b-it	Google	8000	Gemma 2 (27b)
meta-llama/Llama-Vision-Free	Meta	128000	-
mistralai/Mixtral-8x22B-Instruct-v0.1	Mistral AI	64000	Mixtral 8x22B Instruct
Qwen/Qwen2-72B-Instruct	Alibaba Cloud	32000	Qwen 2 Instruct (72B)
mistralai/Mixtral-8x7B-Instruct-v0.1	Mistral AI	64000	Mixtral-8x7B Instruct v0.1
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF	Nvidia	128000	Llama 3.1 Nemotron 70B Instruct
NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO	NousResearch	32000	-
meta-llama/Llama-3.3-70B-Instruct-Turbo	Meta	128000	Meta Llama 3.3 70B Instruct Turbo
meta-llama/Llama-3.2-3B-Instruct-Turbo	Meta	131000	Llama 3.2 3B Instruct Turbo
meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo	Meta	131000	Llama 3.2 11B Vision Instruct Turbo
Qwen/Qwen2.5-7B-Instruct-Turbo	Alibaba Cloud	32000	Qwen 2.5 7B Instruct Turbo
Qwen/Qwen2.5-Coder-32B-Instruct	Alibaba Cloud	131000	-
meta-llama/Meta-Llama-3-8B-Instruct-Lite	Meta	9000	Llama 3 8B Instruct Lite
meta-llama/Llama-3-8b-chat-hf	Meta	8000	Llama 3 8B Instruct Reference
meta-llama/Llama-3-70b-chat-hf	Meta	8000	Llama 3 70B Instruct Reference
meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo	Meta	4000	Llama 3.1 (405B) Instruct Turbo
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo	Meta	128000	Llama 3.1 8B Instruct Turbo
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	Meta	128000	Llama 3.1 70B Instruct Turbo
meta-llama/llama-4-scout	Meta	256000	Coming soon
meta-llama/llama-4-maverick	Meta	256000	Coming soon
mistralai/Mistral-7B-Instruct-v0.2	Mistral AI	32000	Mistral (7B) Instruct v0.2
mistralai/Mistral-7B-Instruct-v0.1	Mistral AI	8000	Mistral (7B) Instruct v0.1
mistralai/Mistral-7B-Instruct-v0.3	Mistral AI	32000	Mistral (7B) Instruct v0.3
Gryphe/MythoMax-L2-13b-Lite	Gryphe	4000	-
claude-3-opus-20240229	Anthropic	200000	Claude 3 Opus
claude-3-haiku-20240307	Anthropic	200000	-
claude-3-5-sonnet-20240620	Anthropic	200000	-
claude-3-5-sonnet-20241022	Anthropic	200000	Claude 3.5 Sonnet 20241022
claude-3-5-haiku-20241022	Anthropic	200000	-
claude-3-7-sonnet-20250219	Anthropic	200000	Claude 3.7 Sonnet
gemini-1.5-flash	Google	1000000	Gemini 1.5 Flash
gemini-1.5-pro	Google	1000000	Gemini 1.5 Pro
gemini-pro	Google	32000	Gemini 1.0 Pro
gemini-2.0-flash-exp	Google	1000000	Gemini 2.0 Flash Experimental
google/gemini-2.0-flash-thinking-exp-01-21	Google	1000000	Gemini 2.0 Flash Thinking Experimental
gemini-2.0-flash	Google	1000000	Coming soon
gemini-2.5-pro-exp-03-25	Google	1000000	Coming soon
google/gemini-2.5-pro-preview	Google	1000000	Coming soon
qwen-max	Alibaba Cloud	32000	Qwen Max
qwen-plus	Alibaba Cloud	131000	Qwen Plus
qwen-turbo	Alibaba Cloud	1000000	Qwen Turbo
qwen-max-2025-01-25	Alibaba Cloud	32000	Qwen Max 2025-01-25
Qwen/Qwen2.5-72B-Instruct-Turbo	Alibaba Cloud	32000	Qwen 2.5 72B Instruct Turbo
Qwen/QwQ-32B	Alibaba Cloud	131000	QwQ-32B
mistralai/mistral-tiny	Mistral AI	32000	Mistral Tiny
x-ai/grok-beta	xAI	131000	Grok-2 Beta
x-ai/grok-3-beta	xAI	131000	Grok 3 Beta
x-ai/grok-3-mini-beta	xAI	131000	Grok 3 Beta Mini
mistralai/mistral-nemo	Mistral AI	128000	Mistral Nemo
neversleep/llama-3.1-lumimaid-70b	Open Source	8000	Llama 3.1 Lumimaid 70b
anthracite-org/magnum-v4-72b	Anthracite	32000	Magnum v4 72B
nvidia/llama-3.1-nemotron-70b-instruct	Nvidia	128000	Llama 3.1 Nemotron 70B Instruct
cohere/command-r-plus	Cohere	128000	Command R+
ai21/jamba-1-5-mini	AI21 Labs	256000	Jamba 1.5 Mini
mistralai/codestral-2501	Mistral AI	256000	Mistral Codestral-2501
MiniMax-Text-01	Minimax AI	1000000	MiniMax-Text-01
abab6.5s-chat	Minimax AI	245000	-

Next Steps

• Learn what a completion is and understand why modern models are often referred to as chat models.