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

# Popular Models

> View detailed information on 400+ supported AI models. Recommended popular and practical AI large models for you.

APIYI supports 400+ mainstream AI models. This page provides detailed model information, pricing, and usage instructions.

<Note>
  **Enterprise-grade Professional and Stable AI Large Model API Hub**
  All models are officially sourced and forwarded, with \~20% off pricing (combining top-up bonuses and exchange rate advantages), aggregating various excellent large models. No speed limits, no expiration, no account ban risks, pay-as-you-go billing, long-term reliable service.
</Note>

## 🔥 Currently Recommended Models

The following are currently stably supplied popular models. For complete model list and real-time pricing, visit [APIYI Console Pricing Page](https://www.apiyi.com/account/pricing).

<Warning>
  **Model Upgrade Recommendations**:  We recommend using the latest models for best performance, but please note:

  1. **Initial instability is common**: Newly launched models may experience slow responses, timeouts, or occasional errors due to limited compute capacity at the vendor — this typically stabilizes within days to weeks
  2. **Check parameter compatibility**: New models may introduce or change parameters (e.g., `max_completion_tokens` replacing `max_tokens`). Before upgrading, verify that your API parameters remain compatible with older models
  3. **Always test before going live**: Before deploying a new model to production, thoroughly validate it in a test environment to ensure output quality and API compatibility meet expectations
</Warning>

## Model Categories

### 🤖 OpenAI Series

#### 🆕 Latest Models

| Model Name           | Model ID        | Context Length | Features                                                                                                            | Recommended Scenarios                             |
| -------------------- | --------------- | -------------- | ------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- |
| **GPT-5.5 Pro**      | `gpt-5.5-pro`   | 1M             | Strongest reasoning today, Terminal-Bench 2.0 82.7%; **`/v1/responses` endpoint + SVIP group only**, very expensive | Top-tier reasoning, research (professional needs) |
| **GPT-5.5** 🔥       | `gpt-5.5`       | 1M             | SWE-bench Verified 88.7%, hallucinations 60% lower than 5.4, new `xhigh` reasoning tier                             | Complex agents, professional workflows            |
| **GPT-5.4**          | `gpt-5.4`       | 1M             | Native computer use, GDPval 83%                                                                                     | Complex agents, professional workflows            |
| **chat-latest**      | `chat-latest`   | 400K           | Version-less alias, always points to the latest ChatGPT Instant (currently GPT-5.5 Instant)                         | Quick writing, conversation                       |
| **GPT-5.2**          | `gpt-5.2`       | 400K           | GDPval 70.9% surpassing professionals                                                                               | Programming planning, structured tasks            |
| **GPT-5.3 Codex** 🔥 | `gpt-5.3-codex` | 128K           | SWE-Bench Pro SOTA, complex programming and agent tasks                                                             | Complex programming, agent tasks                  |
| **GPT-5.1**          | `gpt-5.1`       | 128K           | Intelligence-speed balance, SWE-bench 76.3%, 24h cache                                                              | General apps, programming                         |

<Warning>
  **GPT Pro series (e.g. `gpt-5.5-pro`, `gpt-5-pro`) usage notes**:

  1. **`/v1/responses` endpoint only**: cannot use `/v1/chat/completions` — switch your SDK / code to the Responses API before calling
  2. **Very expensive**: a single call may cost several dollars, and it is open to the SVIP group only to prevent accidental use on the Default group
  3. **Not recommended for non-professional needs**: use GPT-5.5 / GPT-5.4 for everyday tasks; Pro suits only research and top-tier work demanding extreme reasoning depth
</Warning>

#### ✅ Stable / Classic

| Model Name       | Model ID       | Context Length | Features                                        | Recommended Scenarios                |
| ---------------- | -------------- | -------------- | ----------------------------------------------- | ------------------------------------ |
| **GPT-5** ⭐      | `gpt-5`        | 128K           | Flagship stable version, ultra-strong reasoning | Top-tier reasoning, complex tasks    |
| **GPT-5 Mini**   | `gpt-5-mini`   | 128K           | GPT-5 lightweight, excellent performance        | Balance performance and cost         |
| **GPT-5 Nano**   | `gpt-5-nano`   | 128K           | GPT-5 ultra-lightweight                         | Large-scale batch processing         |
| **o3** ⭐         | `o3`           | 200K           | Reasoning model, significantly price-reduced    | Complex reasoning, math, programming |
| **o4-mini**      | `o4-mini`      | 200K           | Lightweight reasoning model                     | Top choice for programming           |
| **GPT-4.1** ⭐    | `gpt-4.1`      | 128K           | Fast speed, main workhorse                      | General applications                 |
| **GPT-4.1 Mini** | `gpt-4.1-mini` | 128K           | Cheaper lightweight version                     | Cost-sensitive scenarios             |
| **GPT-4o**       | `gpt-4o`       | 128K           | Balanced multimodal capabilities                | General scenarios                    |
| **GPT-4o Mini**  | `gpt-4o-mini`  | 128K           | Lightweight fast version                        | Quick response                       |

<Warning>
  **GPT-5 Series Usage Notes**:

  1. Temperature parameter `temperature` must be set to 1 (only supports 1)
  2. Use `max_completion_tokens` instead of `max_tokens`
  3. Do not pass `top_p` parameter
</Warning>

<Info>
  **Image and Video Generation Models** have been moved to a dedicated page. Visit [Image & Video Generation Models](/en/api-capabilities/image-video-models) for the full list and pricing.
</Info>

### 🎭 Claude Series (Anthropic)

#### 🆕 Latest Models

| Model Name                      | Model ID                   | Context Length | Features                                                                                                  | Recommended Scenarios             |
| ------------------------------- | -------------------------- | -------------- | --------------------------------------------------------------------------------------------------------- | --------------------------------- |
| **Claude Opus 4.7** 🔥          | `claude-opus-4-7`          | 1M (Beta)      | Coding benchmarks +13% over 4.6, 3x on production tasks, tool errors cut to 1/3, new xhigh reasoning tier | Top-tier coding, complex agents   |
| **Claude Opus 4.7 Thinking** 🔥 | `claude-opus-4-7-thinking` | 1M (Beta)      | Adaptive thinking, enhanced deep reasoning                                                                | Top-tier reasoning tasks          |
| **Claude Opus 4.6**             | `claude-opus-4-6`          | 1M (Beta)      | Terminal-Bench 2.0 #1, 128K output                                                                        | Top-tier coding, complex agents   |
| **Claude Sonnet 4.6** 🔥        | `claude-sonnet-4-6`        | 1M (Beta)      | Full upgrade, rivals Opus 4.5, great value                                                                | Programming top choice, agent dev |

#### ✅ Stable / Classic

| Model Name                     | Model ID                              | Context Length | Features                                         | Recommended Scenarios                   |
| ------------------------------ | ------------------------------------- | -------------- | ------------------------------------------------ | --------------------------------------- |
| **Claude Opus 4.5** ⭐          | `claude-opus-4-5-20251101`            | 200K           | SWE-bench 80.9%, price reduced to 1/3            | Complex programming, top-tier reasoning |
| **Claude Sonnet 4.5** ⭐        | `claude-sonnet-4-5-20250929`          | 200K           | World-class coding, SWE-bench 77.2%              | Code generation, agent development      |
| **Claude Sonnet 4.5 Thinking** | `claude-sonnet-4-5-20250929-thinking` | 200K           | Chain-of-thought mode, deep reasoning            | Complex programming reasoning           |
| **Claude Haiku 4.5** ⭐         | `claude-haiku-4-5-20251001`           | 200K           | High cost-performance, SWE-bench 73.3%, 2x speed | Real-time chat, pair programming        |
| **Claude 4 Sonnet**            | `claude-sonnet-4-20250514`            | 200K           | Battle-tested, top choice for programming        | Code generation, analysis               |
| **Claude Opus 4.1**            | `claude-opus-4-1-20250805`            | 200K           | Iterative upgrade, programming-optimized         | High-demand programming tasks           |

<Note>
  **Latest**: Claude Opus 4.7 improves coding benchmarks 13% over 4.6, cuts tool-call errors to 1/3, and adds an xhigh reasoning tier at the same price as 4.6. Sonnet 4.6 rivals Opus 4.5 and is now the default on claude.ai. **Stable**: Opus 4.5 and Sonnet 4.5 are battle-tested for production. Haiku 4.5 offers 2x speed at great value.
</Note>

### 🌟 Google Gemini Series

#### 🆕 Latest Models

| Model Name                    | Model ID                 | Context Length | Features                                                                           | Recommended Scenarios                         |
| ----------------------------- | ------------------------ | -------------- | ---------------------------------------------------------------------------------- | --------------------------------------------- |
| **Gemini 3.5 Flash** 🔥       | `gemini-3.5-flash`       | 1M             | Terminal-Bench 2.1 76.2%, fully surpasses 3.1 Pro, \~4x faster at \~half the price | Programming top choice, cost-performance king |
| **Gemini 3.1 Pro Preview** 🔥 | `gemini-3.1-pro-preview` | 1M             | ARC-AGI-2 77.1% (2x+ over 3 Pro), most advanced reasoning                          | Complex reasoning, multimodal analysis        |
| **Gemini 3 Flash Preview**    | `gemini-3-flash-preview` | 1M             | SWE-bench 78%, 3x faster, thinking / nothinking variants available                 | Programming, cost-performance                 |
| **Gemini 3.1 Flash Lite** 🔥  | `gemini-3.1-flash-lite`  | 1M             | GA version, 64% faster than 2.5 Flash, ultra-low price                             | High concurrency, batch, low cost             |

<Warning>
  **Note**: Gemini 3 Pro Preview was discontinued on March 9, 2026. Please migrate to Gemini 3.1 Pro Preview.
</Warning>

#### ✅ Stable / Classic

| Model Name                | Model ID                | Context Length | Features                                                   | Recommended Scenarios              |
| ------------------------- | ----------------------- | -------------- | ---------------------------------------------------------- | ---------------------------------- |
| **Gemini 2.5 Pro** ⭐      | `gemini-2.5-pro`        | 2M             | Official release, programming advantage, strong multimodal | Long text, programming, multimodal |
| **Gemini 2.5 Flash** ⭐    | `gemini-2.5-flash`      | 1M             | Fast speed, low cost, official release                     | Quick response scenarios           |
| **Gemini 2.5 Flash Lite** | `gemini-2.5-flash-lite` | 1M             | Ultra-lightweight, faster and cheaper                      | Large-scale simple tasks           |

<Note>
  **Latest**: Gemini 3.5 Flash fully surpasses Gemini 3.1 Pro on Terminal-Bench 2.1, MCP Atlas and more, at \~4x speed and \~half the price — today's cost-performance king. Gemini 3.1 Pro Preview doubles reasoning (ARC-AGI-2 77.1%), Google's most advanced. Gemini 3.1 Flash Lite is now GA, the cheapest frontier model for high-concurrency. **Stable**: Gemini 2.5 Pro (2M context) and Gemini 2.5 Flash are GA, ideal for production.
</Note>

### 🚀 xAI Grok Series

#### 🆕 Latest Models

| Model Name                   | Model ID                | Context Length | Features                                                                  | Recommended Scenarios              |
| ---------------------------- | ----------------------- | -------------- | ------------------------------------------------------------------------- | ---------------------------------- |
| **Grok 4.3** 🔥              | `grok-4.3`              | 1M             | Intelligence Index 53, τ²-Bench 98%, IFBench 81%, 1M context + multimodal | Complex reasoning, general tasks   |
| **Grok 4**                   | `grok-4`                | Standard       | Official version; `grok-4-all` adds native web search                     | General tasks, real-time info      |
| **Grok 4 Fast Reasoning** 🔥 | `grok-4-fast-reasoning` | 200K           | Reasoning mode, 93%+ cheaper than Grok-4                                  | Complex reasoning                  |
| **Grok Code Fast 1** ⭐       | `grok-code-fast-1`      | 256K           | SWE-bench 70.8%, high-speed generation                                    | Code generation, agent programming |

#### ✅ Stable / Classic

| Model Name      | Model ID      | Context Length | Features                   | Recommended Scenarios |
| --------------- | ------------- | -------------- | -------------------------- | --------------------- |
| **Grok 3** ⭐    | `grok-3`      | Standard       | Official stable version    | Daily use             |
| **Grok 3 All**  | `grok-3-all`  | Standard       | Native web search enhanced | News, market analysis |
| **Grok 3 Mini** | `grok-3-mini` | Standard       | Small model with reasoning | Lightweight tasks     |

### 🔍 DeepSeek Series

#### 🆕 Latest Models

| Model Name               | Model ID            | Context Length | Features                                                                   | Recommended Scenarios             |
| ------------------------ | ------------------- | -------------- | -------------------------------------------------------------------------- | --------------------------------- |
| **DeepSeek V4 Pro** 🔥   | `deepseek-v4-pro`   | 1M             | 1.6T/49B activated, SWE-Verified 80.6 near Claude/Gemini, Hybrid Attention | Complex reasoning, coding, agents |
| **DeepSeek V4 Flash** 🔥 | `deepseek-v4-flash` | 1M             | 284B/13B activated, just \$0.14/M input, open-source SOTA value            | High concurrency, batch           |
| **DeepSeek V3.2**        | `deepseek-v3.2`     | 128K           | GPT-5 level, tool-use in reasoning                                         | Complex reasoning, coding         |

#### ✅ Stable / Classic

| Model Name          | Model ID               | Context Length | Features                                    | Recommended Scenarios              |
| ------------------- | ---------------------- | -------------- | ------------------------------------------- | ---------------------------------- |
| **DeepSeek V3.1** ⭐ | `deepseek-v3-1-250821` | 128K           | Mixed reasoning, Think/Non-Think dual modes | Intelligent reasoning, programming |
| **DeepSeek R1**     | `deepseek-r1`          | 64K            | Reasoning model                             | Math, reasoning                    |
| **DeepSeek V3**     | `deepseek-v3`          | 128K           | Strong comprehensive capabilities           | General scenarios                  |

### 🐘 Chinese Model Series

#### Zhipu AI (GLM)

**🆕 Latest**: GLM-5.1 | **✅ Stable / Classic**: GLM-5, GLM-4.6

| Model Name     | Model ID  | Context Length | Features                                                                                | Recommended Scenarios               |
| -------------- | --------- | -------------- | --------------------------------------------------------------------------------------- | ----------------------------------- |
| **GLM-5.1** 🔥 | `glm-5.1` | 200K           | SWE-Bench Pro 58.4 beats GPT-5.4 / Opus 4.6 / Gemini 3.1 Pro, 744B MoE, MIT open-source | Complex coding, agents              |
| **GLM-5** ⭐    | `glm-5`   | 200K           | 744B params (40B activated), coding aligned with Claude Opus 4.5, open-source           | Complex coding, systems engineering |
| **GLM-4.6**    | `glm-4.6` | 200K           | Code and reasoning enhanced, stable                                                     | Programming, reasoning, agents      |
| **GLM-4.5**    | `glm-4.5` | 128K           | Standard version, strong overall                                                        | General scenarios                   |

<Info>
  **GLM-5.1 Features**:

  * 744B MoE params, supports long-horizon agent tasks up to 8 hours
  * SWE-Bench Pro 58.4, strongest coding among open-source models
  * MIT licensed open-source, excellent value
</Info>

#### Alibaba Qwen

**🆕 Latest**: Qwen3.7-Max | **✅ Stable / Classic**: Qwen Max, Plus, Turbo

| Model Name         | Model ID      | Context Length | Features                                                                                    | Recommended Scenarios           |
| ------------------ | ------------- | -------------- | ------------------------------------------------------------------------------------------- | ------------------------------- |
| **Qwen3.7-Max** 🔥 | `qwen3.7-max` | 1M             | AA Intelligence Index 56.6 (global top 5, #1 in China), 35-hour long-horizon agent autonomy | Agents, multilingual, long text |
| **Qwen Max** ⭐     | `qwen-max`    | 32K            | Strongest stable version                                                                    | General tasks                   |
| **Qwen Plus**      | `qwen-plus`   | 32K            | Enhanced version                                                                            | Cost-effective                  |
| **Qwen Turbo**     | `qwen-turbo`  | 32K            | Fast version                                                                                | Low latency                     |

#### Moonshot Kimi Series

**🆕 Latest**: Kimi K2.6 | **✅ Stable / Classic**: Kimi K2.5, K2

| Model Name                     | Model ID         | Context Length | Features                                                                  | Recommended Scenarios   |
| ------------------------------ | ---------------- | -------------- | ------------------------------------------------------------------------- | ----------------------- |
| **Kimi K2.6** 🔥               | `kimi-k2.6`      | 256K           | 1T MoE / 32B activated, SWE-Bench Pro 58.6 surpasses GPT-5.4 and Opus 4.6 | Coding, agents          |
| **Kimi K2.5**                  | `kimi-k2.5`      | 200K           | Native multimodal, Agent Swarm 100 agents                                 | Multimodal, agents      |
| **Kimi K2 Official Release** ⭐ | `kimi-k2-250711` | 200K           | Volcano Engine partnership, strong stability                              | Production environments |

### 🌐 MiniMax Series

**🆕 Latest**: MiniMax M2.7 | **✅ Stable / Classic**: MiniMax M2.5

| Model Name          | Model ID       | Context Length | Features                                                               | Recommended Scenarios             |
| ------------------- | -------------- | -------------- | ---------------------------------------------------------------------- | --------------------------------- |
| **MiniMax M2.7** 🔥 | `MiniMax-M2.7` | Standard       | 10B params, SWE-bench Pro 56.22%, self-evolving, smallest Tier-1 model | Coding, agents                    |
| **MiniMax M2.5**    | `minimax-m2.5` | Standard       | 230B (10B activated), SWE-bench 80.2%, great value                     | Coding, agents, office automation |

<Info>
  **MiniMax M2.7 Features**:

  * Reaches SWE-bench Pro 56.22% with just 10B params, the smallest Tier-1 model
  * Self-evolving; standard \$0.3 / highspeed (`MiniMax-M2.7-highspeed`) \$0.6 per 1M input tokens
  * Open-sourced model weights
</Info>

## 💰 Pricing Information

### Billing Methods

* **Pay-as-you-go**: Charged based on actual Token usage
* **No minimum charge**: Use what you pay for, balance never expires
* **Real-time deduction**: Fees deducted from balance immediately after each call

### Pricing Advantages

* Official source forwarding with slight price advantages
* Bulk users can contact customer service for better pricing
* New users get 3 million tokens testing credit upon registration

### View Real-time Pricing

Visit [APIYI Console Pricing Page](https://www.apiyi.com/account/pricing) to view latest pricing for all models.

## 🛠️ Usage Recommendations

### Model Selection Guide

**Programming Development**

* Top performance: Claude Opus 4.7 (+13% coding over 4.6), GPT-5.5 (SWE-bench 88.7%), Claude Sonnet 4.6 (rivals Opus 4.5)
* High cost-performance: Gemini 3.5 Flash (surpasses 3.1 Pro at \~half price), GLM-5.1 (SWE-Bench Pro 58.4), Kimi K2.6, DeepSeek V4 Flash
* Alternatives: DeepSeek V4 Pro, Qwen3.7-Max, MiniMax M2.7, o4-mini

**Text Creation**

* Top choice: GPT-5.5, GPT-5.4, Gemini 3.1 Pro Preview, Claude Opus 4.7, Claude Sonnet 4.6
* Alternatives: chat-latest, Claude Sonnet 4.5, GPT-4.1, GPT-4o, Claude Haiku 4.5, GLM-4.6

**Quick Response**

* Top choice: Gemini 3.5 Flash (\~4x speed), Claude Haiku 4.5 (2x faster), GPT-4o Mini
* Alternatives: Gemini 3.1 Flash Lite, Gemini 2.5 Flash, Grok 4 Fast, GPT-4.1 Mini

**Image Generation**

* Latest recommendation: GPT Image 1.5 (4x speed boost, precise editing, from \$0.01)
* Professional design: SeeDream 4.5 (1.2B parameters, 4K quality, \$0.035/image), Nano Banana Pro (4K HD, best text rendering)
* High cost-performance: Nano Banana (\$0.025/image), SeeDream 4.0 (\$0.025/image)
* Reverse-engineered, cheapest: sora\_image, gpt-4o-image

**Long Text Processing**

* Top choice: Gemini 2.5 Pro (2M context)
* Alternatives: Claude 4 series (200K context)

### Cost Optimization Recommendations

1. **Tiered Usage**: Use cheaper models for simple tasks, advanced models for complex tasks
2. **Test Optimization**: Test with small models first, use large models after determining needs
3. **Batch Processing**: Choose Nano or Mini versions for large volumes of similar tasks
4. **Cache Reuse**: Cache results for repeated queries

## 🔗 Related Resources

* [Model Comparison Testing](https://imagen.apiyi.com/) - Image generation effect comparison
* [Real-time Price Query](https://www.apiyi.com/account/pricing) - Latest pricing information
* [API Documentation](/en/api-manual) - Detailed interface specifications
* [Quick Start](/en/getting-started) - Integration guide

<Note>
  Model list is continuously updated. We will promptly add newly released excellent models. For specific model needs or bulk requirements, please contact customer service.
</Note>