Base Models
Discover all the foundation models available on LetzAI
We use our own suite of benchmarks to identify the best AI models from leading providers to serve you only the best and most useful creative tools at all times.
Kling O3 Pro Edit
KuaishouKuaishou's unified multimodal video editor with 7-in-1 capabilities including object removal, background swapping, style changes, and character consistency.
Kling V3
KuaishouKuaishou's flagship video model with native multilingual audio, up to 15 seconds, multi-shot storytelling, and reference image support.
Seedream 4.5
ByteDanceByteDance's image model with multi-image consistency, excellent text rendering, and up to 4K resolution. Maintains character identity across multiple images.
Kling V2.6
KuaishouKuaishou's video model with simultaneous audio-visual generation, creating videos with voiceovers and sound effects in a single pass.
Flux 2
Black Forest LabsBlack Forest Labs' 32B parameter model with multi-reference image support, 4MP editing, improved text rendering, and enhanced photorealism.
Nano Banana Pro
GoogleGoogle's state-of-the-art image generation model with improved text rendering, multi-turn editing, and professional-grade controls over lighting, camera, and composition.
Nano Banana Pro
GoogleGoogle Gemini 3 Pro routed through InferenceSH for improved reliability and per-organization API key support.
Nano Banana Pro Upscaler
GoogleAI-powered upscaling using Google Gemini 3 Pro with intelligent detail enhancement up to 4K resolution.
Magnific Precision V2
FreepikFreepik's faithful upscaler with no hallucinations — preserves text, UI elements, and original image structure with ultimate fidelity.
Veo 3.1 Extend Video
GoogleGoogle's video extension model capable of extending existing videos up to 148 seconds with maintained consistency and style.
Google VEO3.1
GoogleGoogle's updated video model via Vertex AI with richer native audio, improved dialogue sync, and enhanced cinematic style.
Google VEO3.1
GoogleGoogle Veo 3.1 routed through InferenceSH with native audio, improved dialogue sync, and 8-second cinematic video generation.
WAN 2.5
AlibabaAlibaba's open-source video model with multilingual support, synchronized audio, and up to 10 seconds at 1080p resolution.
Gemini 2.5 Flash Image
GoogleGoogle's fast and cost-effective image generation model with support for 10 aspect ratios and image-only output capabilities.
Magnific Creative
FreepikFreepik's creative upscaler that can add and infer new details guided by text prompts, with up to 16x scaling.
LetzAI Upscaler
LetzAILetzAI's in-house upscaler with three modes: Simple (high speed), Sharp (high quality), and Soft (high consistency).
Deprecated Models
These models are no longer available for new generations.
Sora 2
OpenAIOpenAI's realistic video model with physically accurate motion, native audio with synchronized dialogue, and reference image support.
Kling V2.5
KuaishouKuaishou's turbo video model optimized for faster generation with 5-10 second video support.
Default Video
letzaiOur first generation in-house default video model for video generation.
Flux Kontext LoRA
Black Forest LabsBlack Forest Labs' in-context image editing model with LoRA support, enabling iterative multi-turn editing with character and style preservation.
Google Veo 3.0
GoogleGoogle's video generation model via Vertex AI with native audio and cinematic quality at fixed 8-second duration.
LetzAI V3
LetzAIThird generation LetzAI image model with enhanced quality and photorealism based on Flux1.dev.
LetzAI V2
LetzAISecond generation LetzAI image model built on SDXL with improved detail, resolution, and prompt understanding.
LetzAI V1
LetzAIFirst generation LetzAI image model built on Stable Diffusion 1.5 with custom fine-tuning for creative generation.
Our Providers
We partner with leading AI companies to bring you the best models.
Model availability and pricing may change.
Check the pricing page for current rates.
Our models for developers and agents
Our models.json includes the list of all of our models including instructions and their exact capabilities.