Available Models

We now support numerous mainstream AI models. Visit the Model Catalog to explore all supported models.

You can view detailed model information:

• Context length

• Pricing (all kinds of tokens)

• Model release date

Click Connect via API to view the API docs.

Sort Models

You can sort model by the following ways:

• Newest: release or availability date

• Input token price: High → Low: input token price in descending order

• Input token price: Low → High: input token price in ascending order

• Context capacity: High → Low: maximum context capacity

Or just enter the model to search.

Filter Models

Filter by Task Type

Large Language Models (LLMs)

Text-based AI models used for understanding and generating natural language. Suitable for chatbots, content writing, summarization, translation, and reasoning tasks.

Image Generation

Models that generate images based on text prompts. Commonly used for design concepts, illustrations, marketing visuals, and creative content.

Video Generation

Models that generate or edit videos from text or image inputs. Useful for short video creation, visual storytelling, and media production workflows.

Text-to-Speech (TTS)

Models that convert text into spoken audio. Ideal for voice assistants, narration, accessibility features, and audio content creation.

Text Embeddings

Models that convert text into numerical vectors (embeddings). Used for semantic search, recommendation systems, clustering, and similarity matching.

Filter by AI Provider

OpenAI

Provides a wide range of state-of-the-art models for language understanding, generation, and multimodal tasks.

Google

Offers advanced AI models with strong performance in reasoning, multimodal understanding, and large-context processing.

Anthropic

Focuses on reliable and safety-oriented large language models, well-suited for enterprise and regulated use cases.

Perplexity

Specializes in AI models optimized for search, retrieval, and question-answering experiences.

Filter by Context Capacity (MToken)

Context capacity refers to the maximum amount of text a model can process in a single request.

0.2 MToken

Supports short to medium-length inputs. Suitable for simple conversations, prompts, and lightweight tasks.

0.4 MToken

Handles longer inputs such as multi-turn conversations or medium-sized documents.

0.6 MToken

Designed for complex prompts and larger documents requiring deeper context understanding.

0.8 MToken

Supports very long inputs, including large documents or extended multi-turn interactions.

1 MToken

Provides maximum context capacity. Best for processing large datasets, long-form documents, or advanced reasoning tasks with extensive context.