Models

Google Veo 3.1 Fast — balanced speed and quality. Text-to-video and image-to-video with optional reference images and voice narration.

Google Veo 3.1 Fast Relaxed — lower-cost relaxed-priority variant of Veo 3.1 Fast.

Google Veo 3.1 Quality — highest-fidelity Veo 3.1 tier for production-grade output.

Google Veo 3.1 Lite — fastest and most affordable Veo variant. 4–8 second clips.

Google Veo 3.1 Lite Relaxed — lowest-cost relaxed-priority Veo tier.

Google Veo 3.1 Extend — continues an existing clip by up to 8 more seconds. Requires a completed task_id.

Google Veo 3.1 Upscale — upscales a completed video to 1080p or 4K.

Kuaishou Kling 3.0 – flagship model. Up to 15 s single-shot, multi-shot (2–6 scenes), 720p/1080p/4K, native audio on by default.

MiniMax Hailuo 2.0 — text-to-video and image-to-video with 768p/1080p output.

Kuaishou Kling 3.0 multi-shot mode – pass a multi_shots array of 2–6 scenes for connected storytelling.

MiniMax Hailuo 2.3 — latest Hailuo generation with improved motion and detail.

Kuaishou Kling 3.0 Omni – multimodal: text, image, video and reference inputs. Tag images with @image_N in prompt. Up to 7 reference images.

MiniMax Hailuo 2.3 Fast — speed-optimized Hailuo variant. Image-to-video focused.

Kuaishou Kling 2.6 with multi-shot support. Up to 10 s single-shot, 720p/1080p, native audio.

Kuaishou Kling 3.0 Omni — multimodal video with elements, start/end frame, transform and video-reference modes.

Detail-preserving upscaling and restoration up to 4x.

Kuaishou Kling 3.0 Omni Video Edit — edit an existing video with reference or transform mode.

Kuaishou Kling O1 — reasoning-enhanced video generation. Up to 10 seconds.

Kuaishou Kling O1 Video Edit — edit an existing video with reference or transform mode.

Kuaishou Kling 3.0 — flagship video model. Up to 15s, multi-shot, native audio.

Kuaishou Kling 2.6 — image-to-video with voice support and native audio.

Kuaishou Kling 2.5 Turbo — fast text-to-video and image-to-video with sound effects.

Kuaishou Kling 2.1 — image-to-video specialist. Animates a start frame into 5 or 10 seconds.

Kuaishou Kling 2.1 Master — pro-only premium image-to-video.

Kuaishou Kling 2.6 Motion Control — transfer motion from a reference video onto a character image.

Kuaishou Kling 3.0 Motion Control — high-fidelity motion transfer with facial consistency.

ByteDance SeeDance 2.0 Pro – up to 15 s at 1080p. Text-to-video, image-to-video, prompt-references modes. Native audio generation.

Fast text & image to video. Smooth motion, predictable cost per second.

xAI Grok Imagine Video Extend — extend a previously generated video via preset or custom mode.

ByteDance SeeDance 2.0 Fast – faster throughput at lower cost. Same modes and aspect ratios as SeeDance 2.0 Pro.

Topaz Video Upscale — AI video upscaling with selectable models and frame interpolation.

ByteDance SeeDance 1.5 Pro – 5/10/12 s clips at 720p or 1080p. Six aspect ratios, first-and-last-frame interpolation.

Premium cinematic video with reference-to-video and clip extension.

ByteDance SeeDance 1.0 Fast – keyframe array (multi-frame mode), 1080p, text and first-last-frame modes. Reproducible with seed.

ByteDance SeeDance 1.0 Mini – lightest SeeDance model for rapid prototyping and high-volume low-cost use cases.

Natural neural text-to-speech with multiple voices (Tajik, Russian, English).

Google Nano Banana — fast, affordable image generation and editing with strong prompt adherence.

Google Nano Banana Pro — higher-fidelity image generation with 1K/2K/4K resolution.

OpenAI GPT Image 2 — renders text in 50+ languages. Resolution-based (1K/2K/4K) with reference images.

Black Forest Labs Flux.2 Pro — high-quality image generation with up to 8 reference images.

Black Forest Labs Flux.2 Flex — flexible generation with steps and cfg controls.

Black Forest Labs Flux.2 Max — maximum quality image generation.

Kuaishou Kling O1 Image — reasoning-enhanced image generation.

Kuaishou Kling 3.0 Omni Image — high-quality image generation with reference support.

Kuaishou Kling 3.0 Image — batch image generation.

Kuaishou Kling 2.1 Image — image generation with restyle, portrait, character and elements modes.

Topaz Image Upscale — AI image upscaling with selectable presets and face recovery.

Topaz Image Generative — prompt-guided generative image upscaling.

Alibaba Qwen Image 2.0 Pro — best quality with text rendering and realistic textures.

Alibaba Qwen Image 2.0 — faster variant of 2.0 Pro with the same capabilities.

Alibaba Qwen Image Max — highest realism with fewest AI artifacts.

Alibaba Qwen Image Plus — diverse artistic styles with fast generation.

Alibaba Qwen Image — base Qwen image model with text-to-image and editing.

Alibaba Z-Image Turbo — lightweight fast text-to-image with Chinese/English text rendering.

Alibaba Wan 2.7 Pro Image — highest quality with thinking mode and up to 4K.

Alibaba Wan 2.7 Image — faster variant of 2.7 Pro, max 2K resolution.

Alibaba Wan 2.6 Image — image generation with style transfer and editing.

Alibaba Wan 2.5 Image — text-to-image and editing.

Alibaba Wan 2.2 Image — text-to-image generation.

Alibaba Wan 2.2 Flash Image — fast and affordable text-to-image.

xAI Grok Imagine Image — speed-focused image generation and editing.

Suno AI — generate full songs from a prompt with lyrics and style.

Suno AI — add vocals to an uploaded instrumental track.

Suno AI — add instrumental backing to uploaded vocals.

Suno AI — extend an existing song with a new section.

Suno AI — create a cover version of an existing song.

Suno AI — extract vocals and instrumental stems from a track.

Suno AI — extract all individual stems from a track.

Suno AI — generate lyrics from a prompt.

Suno AI — export a clip as WAV, MP3 or M4A.

ElevenLabs — neural text-to-speech with a large voice library.

ElevenLabs — multi-voice dialogue generation.

ElevenLabs — generate sound effects from a text prompt.

ElevenLabs — isolate vocals from an audio track.

ElevenLabs — transcribe audio to text.

Cursor Composer 2.5 — coding model with strong agentic tool use.

Cursor Composer 2.5 Fast — faster, lower-cost coding model.

OpenAI GPT 5.4 Mini — fast, affordable general-purpose model.

OpenAI GPT 5.4 Nano — smallest, fastest GPT 5.4 tier.

OpenAI GPT 5.4 — flagship general-purpose language model.

OpenAI GPT 5.5 — next-generation flagship language model.

OpenAI GPT 5.6 Luna — balanced GPT 5.6 tier.

OpenAI GPT 5.6 Terra — high-capability GPT 5.6 tier.

OpenAI GPT 5.6 Sol — top-tier GPT 5.6 model.

Anthropic Claude Fable 5 — creative writing and storytelling model.

Anthropic Claude Opus 5 — most capable Claude model for complex reasoning.

Anthropic Claude Haiku 4.5 — fast, lightweight Claude model.

Anthropic Claude Opus 4.5 — high-capability reasoning model.

Anthropic Claude Sonnet 4.5 — balanced Claude model.

Anthropic Claude Sonnet 5 — next-generation balanced Claude model.

Anthropic Claude Sonnet 4.6 — strong coding and reasoning model.

Anthropic Claude Opus 4.6 — high-capability reasoning model.

Anthropic Claude Opus 4.7 — high-capability reasoning model.

Anthropic Claude Opus 4.8 — latest high-capability Claude model.

Moonshot AI Kimi K3 — long-context reasoning model (1M context).