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

# Popular Models

> View 200+ supported AI models with detailed information and recommendations

## Model Recommendations

LeapX API supports 200+ mainstream AI models. This page provides detailed model information, pricing, and usage instructions.

<Note>
  Enterprise-grade AI model API gateway. Aggregating excellent large models. No rate limits, no expiration, pay-as-you-go, reliable long-term service.
</Note>

## 🔥 Currently Recommended Models

Below are the currently stable and popular models. For the complete model list and real-time pricing, visit [LeapX API Console](https://leapx-hub.com).

## Model Categories

### 🤖 OpenAI Series

#### Reasoning Models

| Model Name    | Model ID | Features                            | Recommended For                 |
| ------------- | -------- | ----------------------------------- | ------------------------------- |
| **o4-mini**   | o4-mini  | Lightweight reasoning model         | Coding tasks                    |
| **o3-mini** ⭐ | o3-mini  | Latest reasoning model, great value | Complex reasoning, math, coding |

#### GPT Series

| Model Name             | Model ID           | Context | Features                                                                                               | Recommended For                             |
| ---------------------- | ------------------ | ------- | ------------------------------------------------------------------------------------------------------ | ------------------------------------------- |
| **GPT 5.2** ⭐          | gpt-5.2            | 400K    | Improved on GPT-5.1, more reliable, flexible and user-friendly interaction                             | Conversation, thinking, copywriting, coding |
| **GPT 5.1 Codex**      | gpt-5.1-codex      | 400K    | Enhanced developer toolchain, stronger reasoning framework, context-aware code analysis and generation | Conversation, coding, copywriting           |
| **GPT 5.1 Chat**       | gpt-5.1-chat       | 128K    | First to introduce chain-of-thought in chat, faster, more natural, context-aware dialogue              | Conversation, copywriting                   |
| **GPT 5.1**            | gpt-5.1            | 400K    | On-demand reasoning, adaptive reasoning                                                                | Conversation, thinking, copywriting, coding |
| **GPT 5.1 Codex Mini** | gpt-5.1-codex-mini | 128K    | Lightweight and efficient, for resource-constrained, cost-sensitive scenarios                          | Conversation, coding, copywriting           |

#### Image Generation Models

| Model Name      | Model ID    | Features                         |
| --------------- | ----------- | -------------------------------- |
| **GPT-Image-1** | gpt-image-1 | OpenAI official image generation |

### 🎭 Claude Series (Anthropic)

#### Claude 4 Series (Latest)

| Model Name            | Model ID                   | Context | Features                                                                                                | Recommended For                              |
| --------------------- | -------------------------- | ------- | ------------------------------------------------------------------------------------------------------- | -------------------------------------------- |
| **Claude Opus 4.6** ⭐ | claude-opus-4-6            | 1M      | Anthropic's most capable model, sets new standards for production code, complex agents and office tasks | Conversation, reasoning, coding, copywriting |
| **Claude Sonnet 4.5** | claude-sonnet-4-5-20250929 | 200K    | Agent improvements, tool handling, memory and context processing enhanced                               | Conversation, thinking, copywriting, coding  |
| **Claude Haiku 4.5**  | claude-haiku-4-5-20251001  | 200K    | Anthropic's most efficient model, fast and cost-effective near-frontier performance                     | Conversation, thinking, copywriting, coding  |
| **Claude Opus 4.5**   | claude-opus-4-5-20251101   | 200K    | Anthropic's most capable model, sets new standards for production code, complex agents and office tasks | Conversation, thinking, copywriting, coding  |
| **Claude Opus 4.1**   | claude-opus-4-1-20250805   | 200K    | Excellent reasoning capability                                                                          | Conversation, thinking, copywriting, coding  |

### 🌟 Google Gemini Series

| Model Name                 | Model ID               | Context | Features                                                                                | Recommended For                             |
| -------------------------- | ---------------------- | ------- | --------------------------------------------------------------------------------------- | ------------------------------------------- |
| **Nano Banana Pro**        | nano-banana-pro        | 64K     | Gemini 3 Pro Image, versatile image generation model with reasoning in image generation | Text-to-image, image-to-image               |
| **Gemini 3 Flash Preview** | gemini-3-flash-preview | 1M      | Powerful agentic capabilities at speed and value, ideal for multi-turn dialogue         | Conversation, thinking, copywriting, coding |
| **Gemini 3 Pro Preview**   | gemini-3-pro-preview   | 1M      | Powerful agent and coding model, best multimodal understanding                          | Conversation, thinking, copywriting, coding |

### 🚀 xAI Grok Series

| Model Name                | Model ID              | Context | Features                                                                            | Recommended For                             |
| ------------------------- | --------------------- | ------- | ----------------------------------------------------------------------------------- | ------------------------------------------- |
| **Grok-4**                | grok-4                | 256K    | Powerful flagship, unparalleled performance in natural language, math and reasoning | Conversation, thinking, copywriting, coding |
| **Grok-4 Fast Reasoning** | grok-4-fast-reasoning | 2M      | Cost-effective, fast reasoning variant                                              | Conversation, thinking, copywriting, coding |
| **Grok-3**                | grok-3                | 128K    | Enterprise applications, expertise in finance, healthcare, legal and science        | Conversation, copywriting                   |

### 🔍 DeepSeek Series

| Model Name                 | Model ID             | Context | Features                                                                                        | Recommended For                             |
| -------------------------- | -------------------- | ------- | ----------------------------------------------------------------------------------------------- | ------------------------------------------- |
| **DeepSeek V3.1 250821** ⭐ | deepseek-v3.1-250821 | 128K    | New hybrid reasoning model, thinking and non-thinking modes, higher efficiency than DeepSeek-R1 | Conversation, thinking, copywriting, coding |
| **DeepSeek V3**            | deepseek-v3          | 128K    | Strong overall, cost-effective                                                                  | General use                                 |
| **DeepSeek R1**            | deepseek-r1          | 64K     | Reasoning model                                                                                 | Math, reasoning                             |

### 🐘 Chinese Models

#### Zhipu AI (GLM)

| Model Name  | Model ID | Context     | Features                                                               | Recommended For                                               |
| ----------- | -------- | ----------- | ---------------------------------------------------------------------- | ------------------------------------------------------------- |
| **glm-5**   | glm-5    | See console | Latest Zhipu chat model                                                | Conversation, copywriting, coding                             |
| **glm-4.7** | glm-4.7  | 200K        | Latest flagship, stronger coding and multi-step reasoning, 355B params | Conversation, thinking, long-range planning, coding, tool use |

#### Doubao Seed Series

| Model Name          | Model ID               | Context     | Features          | Recommended For           |
| ------------------- | ---------------------- | ----------- | ----------------- | ------------------------- |
| **Doubao Seed 1.8** | doubao-seed-1-8-251228 | See console | Doubao chat model | Conversation, copywriting |

#### Alibaba Qwen

| Model Name           | Model ID         | Context | Features                                                                             | Recommended For                             |
| -------------------- | ---------------- | ------- | ------------------------------------------------------------------------------------ | ------------------------------------------- |
| **Qwen Image Plus**  | qwen-image-plus  | 32K     | Qwen image generation model, 20B params, strong text rendering                       | Text-to-image, image generation             |
| **Qwen3 Coder Plus** | qwen3-coder-plus | 1M      | Code model based on Qwen3, strong Coding Agent, tool use and environment interaction | Conversation, thinking, coding, copywriting |

#### Moonshot Kimi

| Model Name         | Model ID       | Context | Features                                                                                           | Recommended For                             |
| ------------------ | -------------- | ------- | -------------------------------------------------------------------------------------------------- | ------------------------------------------- |
| **kimi-k2.5** ⭐    | kimi-k2.5      | 256K    | Moonshot's most capable model, native multimodal, vision and text, thinking and non-thinking modes | Conversation, thinking                      |
| **Kimi K2 250905** | kimi-k2-250905 | 256K    | MoE architecture, 1T params, 32B active, strong code and Agent capabilities                        | Conversation, thinking, copywriting, coding |

## 💰 Pricing

### Billing

* **Pay-as-you-go**: Billed by actual Token usage
* **No minimum**: Use what you pay for, balance never expires
* **Real-time billing**: Deducted immediately after each call

### Price Advantages

* Official source forwarding with competitive pricing
* Contact support for bulk discounts

## 🛠️ Usage Guide

### Model Selection

<Tabs>
  <Tab title="Coding">
    * **Top Performance**: Claude Opus 4.6, GPT 5.2, Claude Sonnet 4.5
    * **Cost-effective**: Claude Haiku 4.5, GPT 5.1 Codex Mini, DeepSeek V3.1, Grok-4 Fast Reasoning, glm-5
    * **Alternative**: o4-mini, Gemini 3 Pro Preview, Qwen3 Coder Plus, kimi-k2.5, doubao-seed-1-8-251228
  </Tab>

  <Tab title="Writing">
    * **Primary**: GPT 5.2, Claude Opus 4.6, Claude Sonnet 4.5, glm-5
    * **Alternative**: Gemini 3 Pro Preview, Kimi K2, glm-4.7, doubao-seed-1-8-251228
  </Tab>

  <Tab title="Fast Response">
    * **Primary**: Claude Haiku 4.5, Gemini 3 Flash Preview, Grok-4 Fast Reasoning
    * **Alternative**: glm-5, glm-4.7, GPT 5.1 Codex Mini, doubao-seed-1-8-251228
  </Tab>

  <Tab title="Image Generation">
    * **Recommended**: Nano Banana Pro (Gemini 3 Pro Image), Qwen Image Plus, GPT-Image-1
  </Tab>

  <Tab title="Long Text">
    * **Ultra-long context**: Gemini 3 Pro Preview (1M), Claude Opus 4.1 (200K)
    * **Coding**: Claude 4 series, kimi-k2.5, Kimi K2
  </Tab>
</Tabs>

### Cost Optimization

1. **Tiered usage**: Use cheaper models for simple tasks
2. **Test first**: Test with smaller models before scaling
3. **Batch processing**: Use Mini versions for bulk tasks
4. **Cache reuse**: Cache repeated query results

## 🔗 Related Resources

<Columns cols={2}>
  <Card title="API Docs" icon="book" href="/en/api-reference/introduction">
    Detailed API specifications
  </Card>

  <Card title="Quick Start" icon="rocket" href="/en/quickstart">
    Integration guide
  </Card>
</Columns>

<Tip>
  Model list is continuously updated. We add new models as they become available. Contact support for specific model requests or bulk needs.
</Tip>