Search the full model catalog.

Ripple-65B Preview is a 65B-parameter open-weight model from Ricursive Intelligence for agentic coding, reasoning and tool calls. On Wiro a request takes about 15K input tokens and returns up to 8K.

Edit an existing song by regenerating selected time ranges with ElevenLabs Music v2.5. Use chunk plans to swap lyrics, style, or arrangement.

Generate full songs with vocals from a structured composition plan. Control section timing, lyrics, style keywords, and MP3 output quality with ElevenLabs Music v2.5.

Create original music tracks from one written brief using ElevenLabs Music v2.5. Set track length and MP3 quality, and force instrumental-only output when needed.

Write a section-by-section composition plan with lyrics and style cues. ElevenLabs Music v2/v2.5 renders it into a finished MP3 song.

Generate high-fidelity sound effects from a text description with ElevenLabs Sound Effects v3. Built for games, video edits, Foley, and ambient loops.

Upscale a video to 720p, 1080p, 2K, or 4K while keeping aspect ratio and audio. Optionally interpolate frames for output up to 60 fps.

Generate expressive speech from text with MiMo 2.5 TTS by XiaomiMiMo. Use preset voices, design a new voice, or clone a voice from audio.

Xiaomi MiMo-V2.5-ASR is an open-weights speech-to-text model for Chinese and English. It transcribes recordings, including mixed Chinese-English speech, into plain text.

Xiaomi MiMo-V2.6-Distill-Qwen-9B is an open-weights 9B vision-language reasoning model. It answers questions about images and text, with optional step-by-step thinking.

GLM 5.3 is a long-context reasoning model built for complex coding and agent tasks. It handles large projects with a 1M-token context window.

Generate 5–30s videos with KlingAI Kling V4 Reference using text plus reference images, timeline keyframes, and optional video edits at 720p or 1080p.

Kling V4 by KlingAI generates 5–30s videos from a written prompt or keyframe images. Create controlled motion and camera moves in 720p or 1080p.

Generate 4–30s videos from a prompt plus up to 30 images, 10 videos, and 10 audio references. Export MP4/MOV at 480p or 720p, with optional synced audio.

DeepSeek V4.1 Flash Economy is a text-and-vision chat model that answers questions, writes code, and extracts structured facts from very long inputs.

DeepSeek V4.1 Flash is DeepSeek’s 1M-context chat model with native image understanding. Use it for coding, analysis, and agent workflows with tool calls.

Create lip-synced talking-head videos from one portrait plus speech audio or a typed script. Choose voice, language, and 480p or 768p MP4 output.

Turn up to 7 reference images into a character-consistent video with PixVerse C1. Generate 5–15s clips in 360p–1080p, with optional audio.

PixVerse Image to Video C1 animates a still image into a cinematic MP4 clip, up to 1080p and 15 seconds, with optional audio.

Generate 5–15s videos from a prompt plus reference images, clips, and audio. Pruna’s P-Video 2 Pro Reference outputs 480p/768p MP4 with sound.