This documentation portal is designed to help you choose and configure the AI model that best suits your needs—or one of our solutions (ready-to-use tools for specific practical tasks) from our available options and correctly integrate it into your code.

Have suggestions for improvement? Let us know!

Trending Models

from openai import OpenAI
client = OpenAI(
base_url="https://api.aimlapi.com/v1",
api_key="<YOUR_AIMLAPI_KEY>",
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Write a one-sentence story about numbers."}]
)
print(response.choices[0].message.content)

Popular | View all 200+ models >

Select the model by its Task, by its Developer or by the supported Capabilities:

{% hint style="info" %} If you've already made your choice and know the model ID, use the Search panel on your right. {% endhint %}

{% tabs %} {% tab title="Models by TASK" %} {% content-ref url="api-references/text-models-llm/" %} text-models-llm {% endcontent-ref %}

{% content-ref url="api-references/image-models/" %} image-models {% endcontent-ref %}

{% content-ref url="api-references/video-models/" %} video-models {% endcontent-ref %}

{% content-ref url="api-references/music-models/" %} music-models {% endcontent-ref %}

{% content-ref url="api-references/speech-models/" %} speech-models {% endcontent-ref %}

{% content-ref url="api-references/moderation-safety-models/" %} moderation-safety-models {% endcontent-ref %}

{% content-ref url="api-references/3d-generating-models/" %} 3d-generating-models {% endcontent-ref %}

{% content-ref url="api-references/vision-models/" %} vision-models {% endcontent-ref %}

{% content-ref url="api-references/embedding-models/" %} embedding-models {% endcontent-ref %} {% endtab %}

{% tab title="Models by DEVELOPER" %} Alibaba Cloud: Text/Chat Image Video Text-to-Speech

Anthracite: Text/Chat

Anthropic: Text/Chat Embedding

Assembly AI: Speech-To-Text

BAAI: Embedding

ByteDance: Image Video

Cohere: Text/Chat

DeepSeek: Text/Chat

Deepgram: Speech-To-Text Text-to-Speech

ElevenLabs: Text-to-Speech Voice Chat Music

Flux: Image

Google: Text/Chat Image Video Music Vision(OCR) Embedding

Inworld: Text-to-Speech

Kling AI: Video

Krea: Video

LTXV: Video

Meta: Text/Chat

Microsoft: Text-to-Speech

MiniMax: Text/Chat Video Music Voice-Chat

Mistral AI: Text/Chat Vision(OCR)

Moonshot: Text/Chat

NousResearch: Text/Chat

NVIDIA: Text/Chat

OpenAI: Text/Chat Image Speech-To-Text Embedding

Perplexity: Text/Chat

PixVerse: Video

RecraftAI: Image

Reve: Image

Runway: Video

Stability AI: Image Music 3D-Generation

Sber AI: Video

Tencent: Image

Together AI: Embedding

VEED: Video

xAI: Text/Chat Image

Zhipu: Text/Chat {% endtab %}

{% tab title="Text Models by CAPABILITY" %} {% content-ref url="capabilities/completion-or-chat-models.md" %} completion-or-chat-models.md {% endcontent-ref %}

{% content-ref url="capabilities/streaming-mode.md" %} streaming-mode.md {% endcontent-ref %}

{% content-ref url="capabilities/code-generation.md" %} code-generation.md {% endcontent-ref %}

{% content-ref url="capabilities/thinking-reasoning.md" %} thinking-reasoning.md {% endcontent-ref %}

{% content-ref url="capabilities/function-calling.md" %} function-calling.md {% endcontent-ref %}

{% content-ref url="capabilities/image-to-text-vision.md" %} image-to-text-vision.md {% endcontent-ref %}

{% content-ref url="capabilities/web-search.md" %} web-search.md {% endcontent-ref %} {% endtab %} {% endtabs %}

• AI Search Engine – if you need to create a project where information must be found on the internet and then presented to you in a structured format, use this solution.
• OpenAI Assistants – if you need to create tailored AI Assistants capable of handling customer support, data analysis, content generation, and more.

We’re currently working on improving our documentation portal, and your feedback would be incredibly helpful! Take a quick 5-question survey (no personal info required!)

You can also rate each individual page using the built-in form on the right side of the screen: