🎬 Seedance 2.5 at a 28% Discount — Now Live on MuAPI!
ByteDance's next-gen Seedance 2.5 is available exclusively on MuAPI, with text-to-video, image-to-video, first/last-frame, and multi-reference (Omni) endpoints. Generate up to 30-second clips at 480p/720p, starting from $0.17/sec — up to 28% cheaper than other providers.
Featured Models
nano-banana-2-1-edit
Nano Banana 2.1 is Google's latest Gemini image model, delivering fast, high-fidelity image generation and editing up to 4K with strong prompt adherence and legible in-image text.
gemma-4-26b-a4b-abliterated
Gemma 4 26B A4B Abliterated is a Gemma 4 26B A4B mixture-of-experts model with a 65K-token context window and tool-calling support, modified with abliteration to reduce refusal behavior.
glm-5-3-flash-abliterated
GLM 5.3 Flash Abliterated is a fast GLM 5.3 Flash reasoning model with a 1M-token context window, image input and tool-calling support, modified with abliteration to reduce refusal behavior.
gemini-3-8-flash-tts
Gemini 3.8 Flash TTS turns written dialogue into expressive, natural multi-speaker speech with studio-grade voice fidelity, expressive acting, and long-form stability. Control voice, accent, emotional style, and pace per speaker for fast, affordable voiceovers, character dialogue, and narration.
gpt-image-2.5-sunburst-image-to-image
Transform and edit existing images using GPT-Image-2.5 Sunburst, OpenAI's slower, higher-precision GPT Image 2.5 tier, tuned for maximum edit precision on a single critical edit.
wan3.0-spicy-reference-to-video
Wan 3.0 Spicy Reference to Video generates a bold, high-contrast, high-motion video guided by a prompt plus up to 10 reference images, 5 reference videos, and 5 reference audios for visual and audio coherence.
wan3.0-reference-to-video
Wan 3.0 Reference to Video generates a video guided by a prompt plus up to 10 reference images, 5 reference videos, and 5 reference audios for visual and audio coherence.
gemini-3-7-flash
Gemini 3.7 Flash is a high-speed, multimodal language model built for real-time text generation, supporting text and image inputs natively. Token-based pricing: $0.60/M input tokens and $3.60/M output tokens. Two endpoints: standard async (/gemini-3-7-flash) and live streaming (/gemini-3-7-flash/stream) via SSE.
seedance-2.5-omni-reference
Seedance 2.5 Omni Reference blends multiple reference images, video clips, and audio into a single guided generation, with selectable output resolution (480p/720p/1080p/4K) — price scales with the resolution chosen. Supports clips up to 30 seconds.
gemini-3-1-flash-tts
Gemini 3.1 Flash TTS turns written dialogue into expressive, natural multi-speaker speech with fine-grained control over voice, accent, emotional style, and pace. Ideal for fast, affordable voiceovers, character dialogue, and narration.
bytedance-seedream-5.0-pro-edit
Seedream 5.0 Pro Edit is ByteDance's flagship image editing model, extending Seedream 5.0 Lite Edit with higher-fidelity rendering, deeper visual reasoning, and finer typography control. It accepts one or more reference images and a natural-language instruction, targeting up to 2K output with stronger scene composition and richer prompt adherence for professional creative workflows.
gemini-3-5-flash
Gemini 3.5 Flash is a high-speed, multimodal language model built for real-time text generation, supporting text and image inputs natively. Token-based pricing: $0.60/M input tokens and $3.60/M output tokens. Two endpoints: standard async (/gemini-3-5-flash) and live streaming (/gemini-3-5-flash/stream) via SSE.
gpt-image-2-image-to-image
Transform and edit existing images using GPT Image 2 with text instructions. Supports up to 16 input images for precise style transfer, editing, and image transformation.
gpt-image-2-text-to-image
Generate high-quality images from text prompts using GPT Image 2, supporting up to 20,000 character prompts for detailed and precise image creation.
youtube-download
Download videos from YouTube in your chosen resolution or audio format.
nano-banana-2-edit
Nano Banana 2 (Gemini 3.1 Flash Image) is Google's most advanced image generation model, combining speed with high-fidelity 4K output and revolutionary character consistency.
add-image-watermark
Add custom watermark to images with adjustable position, opacity, and size. Free local processing using PIL.
minimax-speech-2.6-hd
Speech-2.6-hd is Minimax’s high-definition text-to-speech model that turns written text into natural, human-like audio. It produces studio-quality speech with clear pronunciation, smooth pacing, realistic emotion, and no background noise.
nano-banana-pro
Nano Banana 2 is the next-generation image generation developed by Google DeepMind, following the original Nano Banana (also known as Gemini 2.5 Flash Image). It offers advanced text-to-image capabilitie with improved resolution.
nano-banana-pro-edit
Nano Banana 2 Edit is the next-generation image editing model developed by Google DeepMind, following the original Nano Banana (also known as Gemini 2.5 Flash Image). It offers advanced image-edit capabilitie with improved resolution.
grok-imagine-image-to-video
Grok Imagine is xAI’s multimodal image-to-video model, capable of animating still images into cinematic videos from 6 to 30 seconds with synchronized ambient audio. It focuses on realism, fluid motion, and expressive lighting transitions while maintaining high generation speed.
nano-banana
Nano Banana is an advanced AI model excelling in natural language-driven image generation and editing. It produces hyper-realistic, physics-aware visuals with seamless style transformations.
ideogram-v3-t2i
Ideogram v3 is an advanced text-to-image model designed for creating highly detailed and visually striking images directly from text prompts. It’s especially good for artistic compositions, design mockups, concept art, and photorealistic scenes. With strong support for text rendering inside images, it’s widely used for posters, typography-based art, and creative branding.
flux-schnell
Flux Schnell is a lightning-fast image generation model designed for rapid iterations. It delivers good visual quality from text prompts almost instantly, making it perfect for real-time concept testing, brainstorming, and UI-integrated experiences.