Base Models
Discover all the foundation models available on LetzAI
Seedance 2.5 Video Upscale
ByteDanceUpscale a video to 1080p via Seedance 2.5 reference-to-video. Max 30s. 4K is not available on 2.5.
Seedance 2.5 Enterprise Video Upscale
ByteDanceOrg-scoped Seedance 2.5 Studio video upscale to 1080p. Max 30s. 4K is not available on 2.5.
BytePlus Video Enhancer
ByteDanceCinema-grade BytePlus MediaKit enhancement (Professional): 30+ algorithms, AI super-res, defect repair, and color. Keeps the original footage (does not regenerate).
Grok 4.6
xAIxAI's newest flagship for coding, agentic tool calling, and long-running visual work. 500k context; reasoning effort low/medium/high/xhigh (default high). Knowledge cutoff February 1, 2026.
Grok Imagine Image Quality
xAIxAI's quality-focused image model — photorealistic rendering, strong text and logo accuracy, and multi-style versatility from portraits to anime. $0.05/image; 1K and 2K.
Seedance 2.0 Video Upscale
ByteDanceUpscale a video to 1080p or 4K via Seedance 2.0 reference-to-video. Max 15s.
Seedance 2.0 Enterprise Video Upscale
ByteDanceOrg-scoped Seedance 2.0 Studio video upscale to 1080p or 4K. Max 15s.
Grok Imagine 2.0
xAIxAI's newest image model — precise instruction following, sharp typography, and iterative editing with up to 5 reference images. $0.04/image; 1K and 2K.
Seedance 2.5 Enterprise
ByteDanceByteDance's professional Seedance 2.5 Studio variant with private asset library support. Automatically uploads reference images to BytePlus virtual portrait library for enhanced character consistency. Up to 30s clips with up to 50 multimodal references (30 images / 10 videos / 10 audio) and synchronized audio. 480p, 720p, and 1080p.
Flux 3 Video
Black Forest LabsBlack Forest Labs' Flux 3 Video — generate and animate video up to 20s at HD or Full HD with synchronized audio. Supports text-to-video, image-to-video (start frame), and first+last frame keyframes. No Omni / multimodal reference stack.
MiniMax H3
MiniMaxMiniMax's frontier video model at 2K. Smart-routes text-to-video, image-to-video (optional last frame), and multimodal reference-to-video (reference images, one video, one audio) while keeping subjects consistent.
Claude Opus 5
AnthropicAnthropic's strongest Opus — step-change over 4.8 for agentic coding, long-horizon work, and professional knowledge tasks. Adaptive thinking; 1M context; near-Fable intelligence at Opus price ($5/$25).
GPT-5.6 Sol
OpenAIOpenAI's GPT-5.6 flagship for complex professional work — coding agents, long research, computer use, and multi-tool workflows. Native web search via the Responses API.
Seedream 5 Pro
ByteDanceByteDance's latest Seedream model with Chain-of-Thought reasoning, enhanced prompt following, reference consistency, and up to 4K resolution.
Seedance 2.5
ByteDanceByteDance's next-generation Seedance with up to 30-second native clips, up to 50 multimodal references (30 images / 10 videos / 10 audio), and synchronized audio. Supports text, image, first+last frame, and reference-to-video. 480p, 720p, and 1080p.
GPT Image 2 Upscaler
Black Forest LabsAI upscaling via OpenAI GPT Image 2 edit with intelligent detail enhancement up to 4K resolution.
Claude Sonnet 5
AnthropicAnthropic's latest Sonnet — drop-in upgrade with adaptive thinking, stronger agentic coding, and 1M context. Introductory pricing through Aug 2026.
Nano Banana 2 Lite
GoogleGoogle's fastest and cheapest Gemini image model — optimized for high-volume generation where speed and cost matter most. Best for single-prompt text-to-image; not optimized for multiple reference inputs or multi-turn editing.
Gemini Omni Flash
GoogleHigh-speed multimodal video with native audio — the cheaper, faster Omni-reference alternative.
Nano Banana 2 Upscaler
GoogleFaster AI upscaling using Google Gemini 3.1 Flash with intelligent detail enhancement up to 4K resolution.
Pruna Upscaler
Pruna AIFast AI upscaling via Pruna P-Image-Upscale with optional detail and realism enhancement up to 128 megapixels.
Beeble SwitchX
BeebleBeeble's video-to-video model that swaps the background or scene in a clip while preserving the original subject, motion, framing and lighting. Not for character or outfit changes. Driven by an optional reference image plus prompt.
Seedance 2.0 Enterprise
ByteDanceByteDance's professional Seedance 2.0 Studio variant with private asset library support. Supports up to 4K (10-bit color), with text-to-video, image-to-video, and multimodal reference-to-video (up to 9 reference images, 3 reference videos, 3 reference audios) and synchronized audio.
GPT-5.5
OpenAIOpenAI's frontier model for complex reasoning, coding, and agentic work. Native web search via the Responses API.
GPT Image 2
OpenAIOpenAI's GPT Image 2 via FAL — exceptional typography, fine-detail rendering, and precise mask-based editing up to 4K.
Seedance 2.0
ByteDanceByteDance's most advanced video model with cinematic output, native audio, real-world physics, and director-level camera control. Supports up to 4K (10-bit color). Supports text, image, audio, and video reference inputs (up to 9 reference images, 3 reference videos, 3 reference audios) with first+last frame control.
WAN 2.7 Image Pro
AlibabaAlibaba's professional image generation model supporting text-to-image, image editing, and multi-reference generation with up to 4K high-definition output. Supports thinking mode for improved quality.
Nano Banana 2
GoogleGoogle's Gemini 3.1 Flash image generation model — fast, cost-effective generation and editing with up to 4K resolution, advanced text rendering, and Google Search grounding.
Nano Banana 2
GoogleGoogle Gemini 3.1 Flash via InferenceSH — fast, cost-effective image generation and editing with up to 4K resolution and Google Search grounding.
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 via InferenceSH with improved retries 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.
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.
WAN 2.5
AlibabaAlibaba's open-source video model with multilingual support, synchronized audio, and up to 10 seconds at 1080p resolution.
How we choose models
Tested by creative professionals
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.
API Access
Integrate LetzAI into your apps, workflows, and agents with our REST API.
Subscribe to any paid plan, then find your key on the subscription page.
Send a POST request to create an image with any model.
POST https://api.letz.ai/imagesPoll the image endpoint with the returned ID until it's ready.
GET https://api.letz.ai/images/:idOur Inference 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.