> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mixroute.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Popular Models
> This page provides detailed model information, pricing, and usage instructions.
## 🔥 Current Recommended Models
Below are the currently stable and popular models. For the complete model list and real-time pricing, please visit [MixRoute Model Marketplace](https://console.mixroute.ai/models).
When calling the API, please ensure the model name matches the naming convention in the [MixRoute Model Marketplace](https://console.mixroute.ai/models); otherwise, the request will fail.
Context values use the model providers' published specifications. MixRoute endpoint support, route aliases, availability, and pricing are governed by the Model Marketplace and each model's detail page.
## Model Categories
### 🤖 OpenAI Series
#### GPT Series
| Model Name | Model ID | Context | Features | Recommended For |
| --------------- | --------------- | ------- | ------------------------------------------------------------------------------------------------------------ | ---------------------------------------------- |
| GPT 5.6 Sol ⭐ | gpt-5.6-sol | 1.05M | Frontier model for complex professional work, with deep reasoning and up to 128K output | Complex reasoning, coding, long-running agents |
| GPT 5.6 Terra | gpt-5.6-terra | 1.05M | Balances intelligence and cost across professional workloads, with up to 128K output | General coding, analysis, content |
| GPT 5.6 Luna | gpt-5.6-luna | 1.05M | Cost-sensitive, high-volume member of the GPT 5.6 family, with up to 128K output | High throughput, routing, batch workloads |
| GPT Chat Latest | gpt-chat-latest | 400K | MixRoute alias for OpenAI's rolling Chat Latest model; the underlying snapshot can change | Chat assistants, prototyping, compatibility |
| GPT 5.5 | gpt-5.5 | 1.05M | Frontier model for coding and professional work; accepts text and image input and supports up to 128K output | Coding, reasoning, professional workflows |
| GPT 5.4 Pro | gpt-5.4-pro | 1.05M | Uses more reasoning compute for precise answers; Responses API only, and complex requests can take longer | High-accuracy analysis and difficult tasks |
| GPT 5.4 | gpt-5.4 | 1.05M | General model for coding and professional work, with Chat Completions and Responses support | Coding, analysis, business content |
#### Image Generation Models
| Model Name | Model ID | Features |
| ------------- | ------------- | ------------------------------------------------------------------ |
| GPT-Image-2 ⭐ | gpt-image-2 | OpenAI's current state-of-the-art image generation model |
| GPT-Image-1.5 | gpt-image-1.5 | Previous-generation image model retained for existing integrations |
| GPT-Image-1 | gpt-image-1 | Earlier image generation model retained for compatibility |
#### Audio, Transcription & Video Models
| Model Name | Model ID | Features | Recommended For |
| ------------------------- | ------------------------- | -------------------------------------------------------------------------------------------- | ------------------------------------ |
| GPT Audio 1.5 ⭐ | gpt-audio-1.5 | OpenAI's best voice model for audio input and output through Chat Completions | Voice assistants, spoken interaction |
| GPT Audio | gpt-audio | Previous audio input/output model for Chat Completions | Existing audio chat integrations |
| GPT-4o Transcribe Diarize | gpt-4o-transcribe-diarize | Speech-to-text that identifies who spoke and when | Meetings, interviews, call analysis |
| GPT-4o Mini Transcribe | gpt-4o-mini-transcribe | Lower-cost GPT-4o mini speech-to-text model | Subtitles, batch transcription |
| Sora 2 ⭐ | sora-2 | Flagship video generation model for text-to-video and image-to-video with synchronized audio | Video creation, creative production |
### 🎭 Claude Series (Anthropic)
#### Latest Claude Models
| Model Name | Model ID | Context | Features | Recommended For |
| ----------------- | ---------------- | ------- | --------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
| Claude Opus 5 ⭐ | claude-opus-5 | 1M | Deep-reasoning model for complex agentic coding and enterprise work; 128K max output and thinking on by default | Long-horizon agents, difficult coding, enterprise work |
| Claude Sonnet 5 ⭐ | claude-sonnet-5 | 1M | Anthropic's best speed-intelligence balance; 128K max output and adaptive thinking on by default | Coding, agents, everyday knowledge work |
| Claude Haiku 4.5 | claude-haiku-4-5 | 200K | Fastest current Claude model, with 64K max output and optional extended thinking | Low-latency chat, routing, extraction |
### 🌟 Google Gemini Series
| Model Name | Model ID | Context | Features | Recommended For |
| ------------------------ | ---------------------- | ------- | --------------------------------------------------------------------------------------------------------- | ----------------------------------------- |
| Gemini 3.6 Flash ⭐ | gemini-3.6-flash | 1M | Production-ready model for agentic coding and multimodal or spatial reasoning, with 64K max output | Coding loops, multimodal analysis, agents |
| Gemini 3.5 Flash-Lite | gemini-3.5-flash-lite | 1M | Low-latency, low-cost model for high-throughput subagents, document parsing, and extraction | Routing, extraction, high-volume tasks |
| Gemini 3.1 Pro Preview | gemini-3.1-pro-preview | 1M | Preview model tuned for software engineering, precise tool use, and reliable multi-step execution | Complex reasoning, coding, tool workflows |
| Gemini 3.1 Flash Image ⭐ | gemini-3.1-flash-image | 128K | Stable high-throughput image generation and editing model with strong text rendering and Search grounding | Image generation, editing, visual content |
### 🚀 xAI Grok Series
| Model Name | Model ID | Context | Features | Recommended For |
| --------------------------------- | ------------------------ | ------- | ------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------ |
| Grok 4.5 ⭐ | grok-4.5 | 500K | Frontier model for coding, agentic tasks, and knowledge work; supports reasoning, tools, and text or image input | Coding, agents, complex knowledge work |
| Grok 4.20 Reasoning | grok-4.20-0309-reasoning | 1M | High-speed reasoning model with agentic tool calling and structured outputs; real-time data requires search tools | Reasoning, research agents, tool workflows |
| Grok 4.3 | grok-4.3 | 1M | Fast general model with strong instruction following, tool calling, structured outputs, and configurable reasoning | Chat, agents, high-volume tool use |
| Grok Build 0.1 (compatibility ID) | grok-code-fast-1 | 256K | xAI routes this compatibility ID to Grok Build 0.1 for agentic software engineering workflows | Coding agents, repository tasks, web development |
### 🔍 DeepSeek Series
| Model Name | Model ID | Context | Features | Recommended For |
| ----------------- | ----------------- | ------- | ---------------------------------------------------------------------------------------------------------------- | ----------------------------------------------- |
| DeepSeek V4 Pro ⭐ | deepseek-v4-pro | 1M | Higher-capability V4 model for reasoning and agentic coding; thinking and non-thinking modes, up to 384K output | Difficult reasoning, coding agents, long tasks |
| DeepSeek V4 Flash | deepseek-v4-flash | 1M | Faster and more economical V4 model with both thinking modes and up to 384K output | High-throughput reasoning, chat, simpler agents |
| DeepSeek V3.2 | deepseek-v3.2 | 164K | Previous-generation model focused on efficient reasoning and reasoning-with-tools workflows | General reasoning, tool use, compatibility |
| DeepSeek V3.1 | deepseek-v3.1 | 128K | Hybrid model with thinking and non-thinking modes plus stronger tool and agent behavior than earlier V3 releases | Chat, reasoning, coding, agents |
### 🐘 Chinese Model Series
#### Zhipu AI (GLM)
| Model Name | Model ID | Context | Features | Recommended For |
| -------------- | -------------- | ------- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------ |
| GLM-5.2 ⭐ | glm-5.2 | 1M | Flagship for project-scale engineering and long-horizon tasks, with 128K max output and configurable reasoning effort | Large repositories, coding agents, long tasks |
| GLM-5.1 | glm-5.1 | 200K | Flagship foundation model for long-running autonomous coding and engineering delivery, with 128K max output | Agentic coding, system optimization, office work |
| GLM-5 Turbo | glm-5-turbo | 200K | Tuned for OpenClaw-style agents, tool calling, instruction following, and persistent multi-step execution | Tool agents, scheduled tasks, automation |
| GLM-5 | glm-5 | 200K | Foundation model for agentic engineering, complex systems, and long-horizon execution | Coding, agents, structured knowledge work |
| GLM-4.7 FlashX | glm-4.7-flashx | 200K | Lightweight, high-speed GLM-4.7 variant with 128K max output and agentic coding support | Fast coding, writing, translation, chat |
#### Alibaba Qwen
| Model Name | Model ID | Context | Features | Recommended For |
| ------------------ | ------------------ | ------- | ----------------------------------------------------------------------------------------- | --------------------------------------------- |
| Qwen Image 2.0 Pro | qwen-image-2.0-pro | — | Image generation and editing up to 2K, with improved realism, details, and text rendering | Text-to-image, image editing, product visuals |
| Qwen 3.7 Max ⭐ | qwen3.7-max | 1M | Largest Qwen 3.7 model; supports hybrid thinking, function calling, and built-in tools | Reasoning, coding, agents, long-context work |
#### Moonshot Kimi Series
| Model Name | Model ID | Context | Features | Recommended For |
| -------------- | -------------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------- |
| Kimi K3 ⭐ | kimi-k3 | 1M | Moonshot's most capable open-weight native multimodal agentic model, designed for long-horizon coding, knowledge work, and reasoning | Large repositories, research, multimodal agents |
| Kimi K2.7 Code | kimi-k2.7-code | 256K | Coding-focused agentic model with image and video input, always-on thinking, and preserved reasoning across turns | Software engineering, coding agents, tool use |
| Kimi K2.6 | kimi-k2.6 | 256K | Native multimodal agentic model for long-horizon coding, proactive execution, and multi-agent orchestration | Coding, visual agents, autonomous workflows |
| Kimi K2.5 | kimi-k2.5 | 256K | Native multimodal model with text, image, and video understanding plus thinking and instant modes | Multimodal chat, reasoning, coding |
#### Seedance & Seedream Series
| Model Name | Model ID | Features |
| :---------------------- | :-------------------------------- | :--------------------------------------------------------------------------------------------------------------------- |
| Dola Seedream 5.0 Pro ⭐ | dola-seedream-5-0-pro-260628 | MixRoute image-generation route with configurable size and quality |
| Seedream 5.0 ⭐ | seedream-5-0-260128 | Text-to-image, image-to-image, multi-image fusion, and high-resolution output |
| Seedream 5.0 Lite | seedream-5-0-lite-260128 | Lower-cost text-to-image and image-to-image generation |
| Seedream 4.5 | seedream-4-5-251128 | Image generation and editing with multi-image fusion, image series, and prompt optimization |
| Seedream 4.0 | seedream-4-0-250828 | Image generation and editing with multi-image fusion, image series, and 2K or 4K output |
| Seedance 2.0 ⭐ | dreamina-seedance-2-0-260128 | Multimodal video generation from text, image, video, and audio references, with synchronized audio and up to 4K output |
| Seedance 2.0 Fast | dreamina-seedance-2-0-fast-260128 | Faster Seedance 2.0 route with multimodal references, synchronized audio, and 480p or 720p output |
| Seedance 2.0 Mini | dreamina-seedance-2-0-mini-260615 | Lightweight Seedance 2.0 route with multimodal references, synchronized audio, and 480p or 720p output |
| Seedance 1.5 Pro | seedance-1-5-pro-251215 | Text-to-video and image-to-video with first and last frames, synchronized audio, and draft mode |
| Seedance 1.0 Pro | seedance-1-0-pro-250528 | Text-to-video and image-to-video with first-frame or first-and-last-frame control |
| Seedance 1.0 Pro Fast | seedance-1-0-pro-fast-251015 | Faster text-to-video and first-frame image-to-video route |
## 🛠️ Usage Recommendations
### Model Selection Guide
**Highest capability**: GPT 5.6 Sol, Claude Opus 5, Kimi K3
**Balanced choices**: GPT 5.6 Terra, Claude Sonnet 5, Gemini 3.6 Flash, Grok 4.5
**Open-model alternatives**: DeepSeek V4 Pro, GLM-5.2, Qwen 3.7 Max
**Recommended**: GPT 5.6 Terra, Claude Sonnet 5, Qwen 3.7 Max
**For difficult research or long material**: GPT 5.6 Sol, Claude Opus 5, Gemini 3.1 Pro Preview
**Recommended**: GPT 5.6 Luna, Claude Haiku 4.5, Gemini 3.5 Flash-Lite
**Alternatives**: Gemini 3.6 Flash, DeepSeek V4 Flash, GLM-4.7 FlashX
**Image**: GPT-Image-2, Gemini 3.1 Flash Image, Seedream 5.0
**Audio**: GPT Audio 1.5, GPT-4o Transcribe Diarize
**Video**: Sora 2, Seedance 2.0
### Long Context Processing
* **1M class**: GPT 5.6 family and GPT 5.5 (1.05M); Claude Opus 5 and Sonnet 5, Gemini 3.6 Flash and 3.1 Pro Preview, DeepSeek V4, GLM-5.2, Qwen 3.7 Max, Kimi K3, and Grok 4.20/4.3 (1M)
* **Coding and agent tasks**: GPT 5.6 Sol, Claude Opus 5, Kimi K3, Grok 4.5, DeepSeek V4 Pro, and GLM-5.2
* **Capacity planning**: Leave room for model output, reasoning tokens, and tool results instead of filling the entire advertised context window
### Cost Optimization Suggestions
1. **Tiered Usage**: Use cheaper models for simple tasks, advanced models for complex tasks
2. **Testing and Optimization**: Test with small models first, scale to larger models once requirements are clear
3. **Batch Processing**: Use Mini versions for a large number of similar tasks
4. **Cache Reuse**: Cache results for repetitive queries
## 🔗 Related Resources
Detailed API reference
Integration guide
Model list is continuously updated. We add newly released excellent models promptly. Contact support for specific models or bulk needs.