> ## Documentation Index
> Fetch the complete documentation index at: https://docs.geekflare.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Supported AI Models

> All Available AI Models in Geekflare Chat.

[Geekflare Chat](http://geekflare.com/ai/chat/) gives you access to the world’s most powerful AI models from top providers in a single workspace. You don't need to manage multiple subscriptions; simply select the model that fits your task from the model dropdown.

> 💡 **Important:**
> Different models require different amounts of compute power. Models are categorized into tiers (Lite, Advanced, and Ultra), and will consume a different number of credits per message.
>
> Before chatting, please review our **[Understanding the Credit System](https://docs.geekflare.com/ai/chat/credit-system)** guide to see exactly how many credits your selected model will cost. The cost is also displayed in the model dropdown interface.

![Credit Info](https://cdn.geekflare.com/api-assets/chat-credit-info.png)

## <Icon icon="openai" size={25} /> OpenAI

OpenAI provides industry-leading models for general conversation, reasoning, and specialized coding tasks.

* GPT-5.5
* GPT-5 Nano
* GPT-5 Mini
* GPT-4.1 Nano
* GPT-4.1 Mini
* GPT-4o Mini
* o4 Mini (Reasoning)
* GPT-5.1 Codex Mini (Coding)
* GPT-5.4
* GPT-5.3 Chat
* GPT-5.3 Codex (Coding)
* GPT-4.1
* GPT-4o
* o3 (Reasoning)
* GPT Image 1
* GPT Image 2

## Google Gemini

Google's Gemini ecosystem is highly optimized for speed, multimodal tasks (images), and wide context windows.

* Gemini 3.5 Flash
* Gemini 3.1 Pro
* Gemini 3 Pro
* Gemini 3 Pro Image (Naon Banana Pro)
* Gemini 3.1 Flash Image (Nano Banana 2)
* Gemini 3 Flash
* Gemini 3.1 Flash Lite

## xAI Grok

Grok models offer exceptionally fast processing and good for social media content.

* Grok Build 0.1
* Grok 4.3
* Grok 4.20 (Reasoning)
* Grok 4.20 (Non-Reasoning)
* Grok 4 Fast (Non-Reasoning)
* Grok Imagine Image

## Anthropic Claude

Claude models are renowned for their nuanced writing, high emotional intelligence, and ability to handle massive documents without losing context.

* Claude Opus 4.7
* Claude Opus 4.6
* Claude Sonnet 4.6
* Claude Haiku 4.5

## Perplexity Sonar

Perplexity models are optimized for search and retrieving up-to-date information.

* Sonar Pro
* Sonar Reasoning
* Sonar

## Mistral

Mistral provides highly efficient, open-weight-style models that are excellent for logic, formatting, and fast text generation.

* Mistral Large 3
* Magistral Medium
* Magistral Small
* Ministral 14B

## MiniMax

MiniMax builds powerful language models to help with everyday tasks, coding, and real-world problem solving.

* MiniMax M3
* Minimax M2.7
* Minimax M2.5

## Qwen

Qwen AI models are built by Alibaba. They are for fast and good for general chat and coding.

* Qwen 3.7 Plus
* Qwen 3.7 Max
* Qwen 3.6 Max
* Qwen 3.5 Flash
* Qwen 3.6 Plus

## Meta Llama

Llama is a family of open AI models by Meta. It is built for flexible, high-performance chat, coding, and multimodal use cases.

* Llama 4 Scout
* Llama 4 Maverick

## Kimi

Kimi by Moonshot AI is focused on long-context models that excel at reading, reasoning, and productivity tasks.

* Kimi K2.6
* Kimi K2.5

## DeepSeek

Fast AI for coding, reasoning, and everyday tasks. Ideal when you want strong performance without high cost.

* DeepSeek V4 Pro
* DeepSeek V4 Flash
* DeepSeek V4 3.2

***

### 🔄 Switching Models Mid-Conversation

You don't have to stick to one model! You can start a conversation with a fast model to brainstorm, and then switch to a reasoning model in the same chat to write code based on your brainstorm.