# MuleRouter MuleRouter is a unified AI model API platform that provides access to multiple AI models through a single API. It supports image generation, video generation, speech synthesis, music generation, and LLM chat models from various vendors. Base URL: `https://api.mulerouter.ai` Platform: https://www.mulerouter.ai Documentation: https://www.mulerouter.ai/docs API Keys: https://www.mulerouter.ai/app/api-keys ## Available Models - [Qwen3.7 Max](https://www.mulerouter.ai/models/qwen3-7-max/llms.txt): Alibaba — Flagship Qwen3.7 LLM with extended context window and explicit cache support for advanced reasoning workloads - [Qwen3.6 Flash](https://www.mulerouter.ai/models/qwen3-6-flash/llms.txt): Alibaba — Latency-optimized Qwen3.6 Flash with tiered pricing (256K boundary), cache support, and up to 1M context - [Qwen3.5 Flash](https://www.mulerouter.ai/models/qwen3-5-flash/llms.txt): Alibaba — Low-latency Qwen3.5 Flash LLM with cache-aware billing for high-throughput chat and tool-use workloads - [GPT 5.4 Mini](https://www.mulerouter.ai/models/gpt-5-4-mini/llms.txt): OpenAI — OpenAI GPT-5.4 Mini - a fast and cost-effective model for lightweight tasks with cached input support - [GPT 5.4 Nano](https://www.mulerouter.ai/models/gpt-5-4-nano/llms.txt): OpenAI — OpenAI GPT-5.4 Nano - the most affordable model in the GPT-5.4 family for high-volume, low-cost workloads - [MiniMax Speech 2.8 Turbo](https://www.mulerouter.ai/models/speech-2-8-turbo/llms.txt): MiniMax — Fast text-to-speech model with 40+ languages, emotion control, voice modification, and interjection tags support - [MiniMax Music 2.0](https://www.mulerouter.ai/models/music-2-0/llms.txt): MiniMax — Music generation model supporting lyrics with structure tags and up to 5-minute songs - [MiniMax Music 2.5](https://www.mulerouter.ai/models/music-2-5/llms.txt): MiniMax — Latest music generation model with improved quality, supporting lyrics with structure tags and up to 5-minute songs - [MiniMax Speech 2.8 HD](https://www.mulerouter.ai/models/speech-2-8-hd/llms.txt): MiniMax — High-definition text-to-speech model with 40+ languages, emotion control, voice modification, and interjection tags supp - [GPT 5.5](https://www.mulerouter.ai/models/gpt-5-5/llms.txt): OpenAI — OpenAI's latest flagship LLM with 1M+ context window, tiered pricing, and cached input support via chat completions and - [GPT Image 2](https://www.mulerouter.ai/models/gpt-image-2/llms.txt): OpenAI — OpenAI's next-generation image model supporting text-to-image generation and image editing up to 4K resolution with mult - [Qwen3.6 Max Preview](https://www.mulerouter.ai/models/qwen3-6-max-preview/llms.txt): Alibaba — Preview of Qwen3.6 Max flagship model with enhanced reasoning, 256K context window, and tiered cache-aware pricing - [Qwen3 VL Flash](https://www.mulerouter.ai/models/qwen3-vl-flash/llms.txt): Alibaba — Fast vision-language model with tiered pricing for efficient multimodal understanding - [Qwen3.5 Omni Flash](https://www.mulerouter.ai/models/qwen3-5-omni-flash/llms.txt): Alibaba — Fast multimodal model supporting text, audio, image, and video inputs with audio output capabilities - [Qwen3 Omni Flash](https://www.mulerouter.ai/models/qwen3-omni-flash/llms.txt): Alibaba — Multimodal model supporting text, audio, image, and video inputs with audio output capabilities - [Qwen3 VL Plus](https://www.mulerouter.ai/models/qwen3-vl-plus/llms.txt): Alibaba — Balanced vision-language model with strong multimodal reasoning and tiered pricing - [GLM 5.1](https://www.mulerouter.ai/models/glm-5-1/llms.txt): Z.ai AI — Z.ai GLM 5.1 large language model with tiered pricing and cache support - [Qwen3.6 Plus](https://www.mulerouter.ai/models/qwen3-6-plus/llms.txt): Alibaba — Qwen3.6 Plus multimodal model with 1M context, vision understanding, enhanced code capabilities, and extended reasoning - [Qwen VL Max](https://www.mulerouter.ai/models/qwen-vl-max/llms.txt): Alibaba — Flagship vision-language model with premium multimodal understanding and reasoning - [Qwen3.5 Omni Plus](https://www.mulerouter.ai/models/qwen3-5-omni-plus/llms.txt): Alibaba — Premium multimodal model supporting text, audio, image, and video inputs with audio output capabilities - [Kling V3 Omni](https://www.mulerouter.ai/models/kling-v3-omni/llms.txt): KlingAI — Kling V3 Omni video generation model with text-to-video, image-to-video, reference-to-video, and video-to-video capabili - [Kling V3](https://www.mulerouter.ai/models/kling-v3/llms.txt): KlingAI — Latest Kling video generation model with multi-shot, audio generation, element reference, and 3-15s duration support - [Nano Banana 2](https://www.mulerouter.ai/models/nano-banana-2/llms.txt): Google — Next-generation image generation and editing model with 4K support, 14 aspect ratios, and web search grounding - [Qwen3.5 Plus](https://www.mulerouter.ai/models/qwen3-5-plus/llms.txt): Alibaba — Latest Qwen flagship model with 1M context window, native multimodal understanding, built-in tool use, and advanced reas - [Grok Code Fast 1](https://www.mulerouter.ai/models/grok-code-fast-1/llms.txt): X.AI — Specialized code generation model with fast inference and reasoning - [Qwen3 Max Thinking](https://www.mulerouter.ai/models/qwen3-max-thinking/llms.txt): Alibaba — Latest Qwen3 flagship model with improved reasoning and extended context capabilities - [Qwen Image Max](https://www.mulerouter.ai/models/qwen-image-max/llms.txt): Alibaba — text-to-image model with enhanced realism and text rendering - [Qwen Image Edit Max](https://www.mulerouter.ai/models/qwen-image-edit-max/llms.txt): Alibaba — Premium image editing model with enhanced quality - supports multi-image input/output, text modification, and advanced e - [Grok 4](https://www.mulerouter.ai/models/grok-4/llms.txt): X.AI — Advanced reasoning model with extended context and cached input support - [Wan 2.5 Text-To-Video Spark](https://www.mulerouter.ai/models/wan2-5-t2v-spark/llms.txt): MuleRouter — Cost-effective text-to-video generation fine-tuned by MuleRouter. Get similar quality at a lower price with 720P/1080P s - [Wan 2.6 Text-To-Video Spark](https://www.mulerouter.ai/models/wan2-6-t2v-spark/llms.txt): MuleRouter — Cost-effective text-to-video generation fine-tuned by MuleRouter. Get similar quality at a lower price with 1080P suppor - [Wan 2.5 Image-To-Video Spark](https://www.mulerouter.ai/models/wan2-5-i2v-spark/llms.txt): MuleRouter — Cost-effective image-to-video generation fine-tuned by MuleRouter. Get similar quality at a lower price with 720P/1080P - [Wan 2.6 Image-To-Video Spark](https://www.mulerouter.ai/models/wan2-6-i2v-spark/llms.txt): MuleRouter — Cost-effective image-to-video generation fine-tuned by MuleRouter. Get similar quality at a lower price with 1080P suppo - [Wan 2.6 Image-To-Video](https://www.mulerouter.ai/models/wan2-6-i2v/llms.txt): Alibaba — Converts a single image into a coherent, high-quality video with smooth motion. - [Wan 2.6 Text-To-Video](https://www.mulerouter.ai/models/wan2-6-t2v/llms.txt): Alibaba — Generates high-quality, coherent videos directly from text prompts. - [Wan 2.5 Image-To-Video Preview](https://www.mulerouter.ai/models/wan2-5-i2v-preview/llms.txt): Alibaba — Image-to-video with advanced motion synthesis - [Qwen3 Plus](https://www.mulerouter.ai/models/qwen-plus/llms.txt): Alibaba — Balanced Qwen3 tier combining strong reasoning with cost efficiency - [Qwen3 Flash](https://www.mulerouter.ai/models/qwen-flash/llms.txt): Alibaba — Latency-optimized Qwen3 inference for chat and tool use at scale - [Qwen3 Max](https://www.mulerouter.ai/models/qwen3-max/llms.txt): Alibaba — Flagship Qwen3 model for expansive reasoning and extended context windows - [Wan 2.5 Text-To-Video Preview](https://www.mulerouter.ai/models/wan2-5-t2v-preview/llms.txt): Alibaba — Text-to-video generation with flagship quality and control - [Wan 2.1 Keyframe-To-Video Plus](https://www.mulerouter.ai/models/wan2-1-kf2v-plus/llms.txt): Alibaba — Keyframe-to-video for controlled sequences - [Wan 2.1 Video Ace Plus](https://www.mulerouter.ai/models/wan2-1-vace-plus/llms.txt): Alibaba — Video face editing with tracking capabilities - [Wan 2.2 Image-To-Video Flash](https://www.mulerouter.ai/models/wan2-2-i2v-flash/llms.txt): Alibaba — Ultra-fast image-to-video for previsualization - [Wan 2.2 Image-To-Video Plus](https://www.mulerouter.ai/models/wan2-2-i2v-plus/llms.txt): Alibaba — Speed-optimized image-to-video generation - [Wan 2.2 Text-To-Video Plus](https://www.mulerouter.ai/models/wan2-2-t2v-plus/llms.txt): Alibaba — Fast text-to-video for rapid iteration - [Wan 2.5 Image-To-Image Preview](https://www.mulerouter.ai/models/wan2-5-i2i-preview/llms.txt): Alibaba — Image-to-image transformation and editing - [Wan 2.5 Text-To-Image Preview](https://www.mulerouter.ai/models/wan2-5-t2i-preview/llms.txt): Alibaba — Text-to-image generation with high fidelity - [Nano Banana Pro](https://www.mulerouter.ai/models/nano-banana-pro/llms.txt): Google — Versatile edit model combining image-to-image transformation and inpainting capabilities ## Links - [All Models](https://www.mulerouter.ai/) - [Documentation](https://www.mulerouter.ai/docs) - [API Keys Management](https://www.mulerouter.ai/app/api-keys)