Introduction

Welcome to Flaq.ai - your gateway to cutting-edge AI image, video, 3D, music, and LLM models.

What is Flaq.ai

Flaq.ai is a powerful AI generation platform that provides unified access to state-of-the-art image, video, 3D, music, and LLM models from leading AI providers including Google, ByteDance, Alibaba, DeepSeek, Tripo3D AI, Meshy, and Mureka.

Our platform simplifies the integration of advanced AI models into your applications through a consistent, easy-to-use API interface. Whether you're building creative tools, automating content generation, or exploring AI capabilities, Flaq.ai provides the infrastructure you need.

Key Features

Unified API: Consistent API interface across all models for seamless integration
High-Quality Output: Generate professional-grade images, videos, 3D models, and music with advanced AI technology
Flexible Parameters: Fine-tune generation with aspect ratios, styles, and model-specific controls
Fast Processing: Optimized infrastructure for quick generation and delivery
Developer-Friendly: Comprehensive documentation, code examples, and SDKs

Supported Models

Image Generation Models

Nano Banana Pro (Google Gemini 3.0 Pro Image)
Premier AI-powered visual generation with native 4K output, context-aware understanding, and multilingual typography.
Nano Banana Pro Edit (Google Gemini 3.0 Pro Image Edit)
Advanced image editing capabilities with precise control over modifications and enhancements.
Nano Banana 2 (Google Gemini 3.1 Flash Image)
Lightning-fast AI image generation optimized for cost-effectiveness and high-performance. Benchmarked against Nano Banana Pro with exceptional speed while maintaining professional quality.
Nano Banana 2 Edit (Google Gemini 3.1 Flash Image Edit)
Fast and efficient image editing with natural language commands, offering rapid iteration and precise adjustments at optimized cost.
Seedream 4.5 (ByteDance)
Fast, stylized generation with strong anime and illustration aesthetics.
Seedream 5.0 (ByteDance)
Next-generation image generation with enhanced prompt adherence, superior detail rendering, and improved aesthetic quality.
Seedream 5.0 Edit (ByteDance)
Advanced image editing powered by Seedream 5.0, supporting precise instruction-based modifications.
Seedream 5.0 Pro (ByteDance)
Premium text-to-image generation with enhanced prompt adherence, superior detail rendering, and support for eight aspect ratios including 21:9.
Seedream 5.0 Pro Edit (ByteDance)
High-fidelity image editing powered by Seedream 5.0 Pro, supporting instruction-based modifications with 1–10 reference images.
Qwen Image 2.0 (Alibaba)
High-performance image generation with sharp text rendering and realistic visuals. Optimized for stable, high-quality output at competitive pricing.
Qwen Image 3.0 (Alibaba)
High-quality text-to-image generation with strong prompt adherence and flexible composition control.
Qwen Image 3.0 Edit (Alibaba)
Instruction-based image editing with multi-image input support and precise visual refinement.
Qwen Image 3.0 Pro (Alibaba)
Professional text-to-image generation with knowledge-rich composition and multilingual text rendering.
Qwen Image 3.0 Pro Edit (Alibaba)
High-fidelity image editing with multi-image composition, instruction-based modifications, and consistent visual refinement.
Qwen Image Lora Edit (Alibaba)
Prompt-guided image editing for background changes, style updates, object edits, and polished production-ready visual refinements.
Wan 2.7 Image Pro (Alibaba)
Premium text-to-image generation from Alibaba's Wan 2.7 series, delivering enhanced visual quality with support for seven aspect ratios including 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.
Wan 2.7 Image Pro Edit (Alibaba)
High-fidelity image-to-image editing powered by Wan 2.7 Image Pro Edit, supporting instruction-based modifications with 1–9 reference images for precise visual refinement.
Wan 2.7 Image (Alibaba)
Cost-effective text-to-image generation from the Wan 2.7 series, ideal for high-volume creative workflows with flexible aspect ratio control.
Wan 2.7 Image Edit (Alibaba)
Instruction-based image editing with multi-image input support, enabling efficient visual modifications at competitive pricing.
Z Image (Alibaba)
Affordable text-to-image generation for marketing visuals, product imagery, social assets, and creative automation workflows.
Grok Imagine (xAI)
Image generation powered by xAI's Grok, delivering creative and diverse visual outputs.
Grok Imagine Edit (xAI)
Instruction-based image editing with Grok's understanding of complex natural language commands.
GPT Image 2 (OpenAI)
High-quality text-to-image generation with strong prompt adherence, flexible quality controls, and reliable typography rendering for production workflows.
GPT Image 2 Edit (OpenAI)
Prompt-driven image editing with support for multi-image inputs, context-aware modifications, and consistent visual preservation across complex edits.
GPT Image 2 Client (OpenAI)
OpenAI GPT Image 2 generation access through the client variant, offering the same core text-to-image workflow for teams standardizing on this route.
GPT Image 2 Edit Client (OpenAI)
Client-route access to GPT Image 2 editing, supporting instruction-based edits, multi-image composition, and flexible creative refinement workflows.
ChatGPT Images 2.5 (OpenAI)
Cost-effective text-to-image generation with flexible aspect ratios for product imagery, marketing assets, and creative workflows.
ChatGPT Images 2.5 Edit (OpenAI)
Instruction-based image editing with multiple reference images and flexible aspect ratios for visual refinement and composition.
ChatGPT Images 2.5 Client (OpenAI)
Affordable access to the same core ChatGPT Images 2.5 text-to-image workflow through the Client variant for creative applications.
ChatGPT Images 2.5 Edit Client (OpenAI)
Affordable access to the same core ChatGPT Images 2.5 editing workflow through the Client variant, supporting edits with 1–16 input images.
ChatGPT Images 2.5 Flare / Sunburst (OpenAI)
Text-to-image generation with flexible aspect ratios, resolution options, and quality controls.
ChatGPT Images 2.5 Flare Edit / Sunburst Edit (OpenAI)
Prompt-guided editing with 1–16 reference images and the same output controls.
Nano Banana 2.1 (Google)
Efficient text-to-image generation with improved prompt adherence, detailed visuals, and clear text rendering.
Nano Banana 2.1 Edit (Google)
Instruction-based image editing with up to 14 reference images for detailed, visually consistent refinements.

Video Generation Models

Veo 3.1 Text to Video (Google)
High-quality video generation from text prompts with advanced motion synthesis.
Veo 3.1 Image to Video (Google)
Transform static images into dynamic videos with sophisticated motion effects.
Veo 3.1 Fast Text to Video (Google)
Rapid video generation from text prompts, optimized for processing speed.
Veo 3.1 Fast Image to Video (Google)
Faster image-to-video conversion with reduced processing time.
Wan 2.6 Text to Video (Alibaba)
Advanced text-to-video synthesis delivering high-quality outputs.
Wan 2.6 Image to Video (Alibaba)
Sophisticated image-to-video transformation featuring complex motion and scene composition.
Wan 2.7 Text to Video (Alibaba)
Next-generation text-to-video synthesis with improved motion quality and prompt adherence over Wan 2.6.
Wan 2.7 Image to Video (Alibaba)
Advanced image-to-video transformation with enhanced scene dynamics and temporal consistency.
Wan 2.7 Lora (Alibaba)
Advanced Wan 2.7 animation workflows for turning still visuals into cinematic motion with prompt-guided camera movement and stable subject preservation.
Wan 2.7 Video Edit (Alibaba)
AI-powered video editing that applies text-guided modifications to existing video content.
MiniMax H3 (MiniMax)
Video generation family supporting text-to-video, start-and-end-frame image-to-video, and multimodal reference-to-video workflows with image, video, and audio inputs.
Happy Horse 1.0 (Alibaba)
High-quality video generation model supporting both text-to-video and image-to-video workflows, with flexible clip creation for creative and production use cases.
Seedance 1.5 Pro (ByteDance)
Native audio-visual sync video model with multilingual lip-sync capabilities and cinematic quality for professional video production.
Seedance 2.0 (ByteDance)
Next-generation audio-visual video model with standard and fast variants, supporting text-to-video, image-to-video, and reference-to-video generation modes.
Seedance 2.5 (ByteDance)
Video generation family supporting text-to-video, first-frame image-to-video with optional end-frame guidance, and reference-to-video workflows with video, image, and audio inputs.
Kling 3.0 (Kuaishou)
Efficient video generation with solid physical coherency and smooth scene transitions, ideal for dynamic content creation.
Kling 3.0 Turbo (Kuaishou)
Fast Kling video generation for text-to-video and image-to-video workflows with optional sound, designed for quick creative iteration and production use.
Kling Video O3 (Kuaishou)
Advanced reasoning-enhanced video model supporting text-to-video, image-to-video, reference-to-video, and video editing in both standard and pro tiers.
Vidu Q3 (Vidu)
High-quality video generation with turbo and pro variants, supporting text-to-video, image-to-video, and start-end frame control.
Pixverse C1 (PixVerse)
Text-to-video, first-frame image-to-video, and first-and-last-frame transition generation with flexible resolution and duration controls.
Pixverse V6 (PixVerse)
Text-to-video, image-to-video, transition, and video extend workflows with optional negative prompts and seeding on transition and extend variants.
Grok Imagine Video (xAI)
AI video generation by xAI, supporting both text-to-video and image-to-video creation.
Grok Imagine Video 1.5 (xAI)
Next-generation image-to-video animation by xAI with expanded aspect ratio support and flexible duration options.
Video Upscaler (Flaq AI)
Accessible video enhancement for improving the resolution and visual quality of existing footage through a simple video-to-video workflow.
Video Upscaler Pro (Flaq AI)
Quality-focused video enhancement for refining existing footage across professional media and production workflows.
Happy Horse 1.1 (Alibaba)
Versatile video generation for text-to-video, image-to-video, and reference-guided creative workflows.
Seedance 2.0 Mini (ByteDance)
Cost-effective video generation for efficient text-to-video, image-to-video, and reference-to-video workflows.
FLUX 3 (Black Forest Labs)
Video generation family supporting text-to-video, image-to-video, start-and-end-frame transitions, and video extension with native audio.
Wan 3.0 (Alibaba)
Video generation family supporting text-to-video, required start-and-end-frame image-to-video, prompt-guided video editing, and multimodal reference-to-video workflows.
Gemini Omni 1.1 Flash (Google)
Video generation family supporting text-to-video, required start-frame and optional end-frame image-to-video, source-video editing, and reference-to-video workflows with optional image and video inputs.

3D Generation Models

Tripo H3.1 Text to 3D (Tripo3D AI)
Generate a 3D model from a text prompt with configurable texture, PBR material, geometry, scale, and mesh settings.
Tripo H3.1 Image to 3D (Tripo3D AI)
Reconstruct a 3D model from one reference image with texture alignment and model orientation controls.
Tripo H3.1 Multiview to 3D (Tripo3D AI)
Build a 3D model from two to four ordered front, left, back, and right reference images.
Meshy 7 Text to 3D (Meshy)
Generate a 3D model from a text prompt with topology, polygon count, remesh, pose, and optional PBR texture controls.
Meshy 7 Image to 3D (Meshy)
Generate a 3D model from one reference image with configurable mesh, symmetry, pose, and texture settings.
Meshy 7 Multiview to 3D (Meshy)
Generate a 3D model from one to four reference images without a fixed view order, with mesh and texture controls.

Music Generation Models

Mureka 9.5 Generate BGM (Mureka)
Generate instrumental background music from a text description with selectable audio output formats.
Mureka 9.5 Generate Song (Mureka)
Turn supplied lyrics into songs with optional style guidance, vocal ID, and audio format selection.
Mureka 9.5 Prompt to Song (Mureka)
Generate complete songs with optional text descriptions, style tags, vocal ID, and audio format selection.
Mureka O2 Generate Song (Mureka)
Generate songs from supplied lyrics with optional style guidance, vocal ID, and audio format selection.

LLM Models

GPT 5.4 (OpenAI)
Fast and affordable OpenAI LLM API access for text-to-text, image-to-text, web search, and file analysis workflows.
GPT 5.5 (OpenAI)
Advanced OpenAI LLM access for reasoning, coding help, multimodal understanding, web-aware answers, and deep document analysis.
GPT 5.6 Sol (OpenAI)
Flagship OpenAI LLM access for advanced reasoning, coding, writing, multimodal understanding, web-aware answers, and professional file analysis workflows.
GPT 5.6 Terra (OpenAI)
Balanced OpenAI LLM access for dependable reasoning, writing, coding help, visual understanding, web research, and cost-effective document analysis.
GPT 5.6 Luna (OpenAI)
Fast and affordable OpenAI LLM access for high-throughput chat, writing, coding, image understanding, web search, and document analysis workflows.
Claude Sonnet 4.6 (Anthropic)
Balanced Claude LLM API for fast reasoning, writing, coding help, and file analysis with stable production access.
Claude Sonnet 5 (Anthropic)
Latest balanced Claude LLM API for fast reasoning, writing, coding help, and file analysis with stable production access.
Claude Opus 4.6 (Anthropic)
High-capability Claude Opus model for careful reasoning, complex writing, coding support, and document review workflows.
Claude Opus 4.7 (Anthropic)
Latest Claude Opus LLM for advanced reasoning, technical analysis, file understanding, and professional AI applications.
Claude Opus 4.8 (Anthropic)
Most capable Claude Opus model for complex reasoning, deep technical analysis, file and image understanding, and advanced AI workflows.
Claude Opus 5 (Anthropic)
Advanced Claude Opus LLM for demanding reasoning, writing, coding, and file or image analysis through text-to-text and file-analysis variants.
Claude Fable 5 (Anthropic)
Mythos-class Claude LLM for long-horizon reasoning, agentic coding, web-aware research, and file or image analysis through text-to-text, web search, and file analysis variants.
Gemini 3.5 Flash (Google)
Fast and efficient Google LLM for text generation, image understanding, and file analysis with low-latency responses.
Gemini 3.6 Flash (Google)
Efficient Google Flash LLM for text generation, image understanding, and file analysis, combining improved token efficiency with coding and agentic planning support.
Gemini 3.7 Flash (Google)
Google's latest Flash LLM for complex coding, agentic workflows, multi-step reasoning, image understanding, and file analysis through a highly cost-effective API configuration.
Qwen 3.7 (Alibaba)
Alibaba's reasoning LLM with Max and Plus tiers, supporting text generation and web-search-augmented answers.
Qwen 3.8 Max (Alibaba)
Max-tier Alibaba LLM for advanced text reasoning and web-search-augmented answers, with streaming and flexible generation controls.
Qwen Character (Alibaba)
Alibaba character roleplay LLMs with Plus and Flash tiers, supporting persona-driven chat, reusable profiles, memory-aware dialogue, and scalable storytelling workflows.
DeepSeek v4 (DeepSeek)
DeepSeek LLM access with Pro and Flash tiers for text generation, reasoning, coding help, and web-search-augmented answers for current-information workflows.
Kimi 2.7 (Moonshot AI)
Moonshot AI LLM access for text reasoning and image-to-text understanding, supporting writing, coding, visual analysis, OCR-style extraction, and multimodal assistant workflows.
GLM 5.2 (Z.ai)
Advanced Z.ai LLM for practical reasoning, coding help, structured text generation, and agent-oriented engineering workflows through a production-ready text-to-text API.
Grok 4 (xAI)
High-performance xAI LLM for text reasoning and image understanding with strong analytical capabilities.
Grok 4.5 (xAI)
Advanced xAI LLM for text generation, reasoning, coding assistance, and multimodal image understanding across analytical and conversational workflows.
Grok 4.6 (xAI)
Latest xAI LLM for advanced reasoning, coding, engineering, professional knowledge work, and image understanding through text-to-text and image-to-text variants.
Kimi K3 (Moonshot AI)
Moonshot AI text-only LLM access for long-horizon coding, reasoning, knowledge work, and scalable agent workflows.
GPT 6 Astra (OpenAI)
Advanced OpenAI LLM access for complex reasoning, coding, visual understanding, web research, and document analysis through text-to-text, image-to-text, web search, and file analysis variants.
Claude Fable 5.1 (Anthropic)
Advanced Claude LLM access for complex coding, knowledge work, web research, and file or image analysis through text-to-text, web search, and file analysis variants.
GPT 6 Sol (OpenAI)
OpenAI LLM access for writing, coding, conversation, image understanding, web research, and document analysis through text-to-text, image-to-text, web search, and file analysis variants.
GPT 6 Luna (OpenAI)
OpenAI LLM access for text generation, coding assistance, visual questions, online research, and file summaries through text-to-text, image-to-text, web search, and file analysis variants.
Claude Opus 5.5 (Anthropic)
Claude Opus LLM access for text reasoning, writing, coding, document review, and file or image analysis through text-to-text and file analysis variants.

What is Flaq.ai

Key Features

Unified API: Consistent API interface across all models for seamless integration

High-Quality Output: Generate professional-grade images, videos, 3D models, and music with advanced AI technology

Flexible Parameters: Fine-tune generation with aspect ratios, styles, and model-specific controls

Fast Processing: Optimized infrastructure for quick generation and delivery

Developer-Friendly: Comprehensive documentation, code examples, and SDKs

Supported Models

Image Generation Models

Nano Banana Pro (Google Gemini 3.0 Pro Image)
Premier AI-powered visual generation with native 4K output, context-aware understanding, and multilingual typography.

Nano Banana Pro Edit (Google Gemini 3.0 Pro Image Edit)
Advanced image editing capabilities with precise control over modifications and enhancements.

Nano Banana 2 (Google Gemini 3.1 Flash Image)
Lightning-fast AI image generation optimized for cost-effectiveness and high-performance. Benchmarked against Nano Banana Pro with exceptional speed while maintaining professional quality.

Nano Banana 2 Edit (Google Gemini 3.1 Flash Image Edit)
Fast and efficient image editing with natural language commands, offering rapid iteration and precise adjustments at optimized cost.

Seedream 4.5 (ByteDance)
Fast, stylized generation with strong anime and illustration aesthetics.

Seedream 5.0 (ByteDance)
Next-generation image generation with enhanced prompt adherence, superior detail rendering, and improved aesthetic quality.

Seedream 5.0 Edit (ByteDance)
Advanced image editing powered by Seedream 5.0, supporting precise instruction-based modifications.

Seedream 5.0 Pro (ByteDance)
Premium text-to-image generation with enhanced prompt adherence, superior detail rendering, and support for eight aspect ratios including 21:9.

Seedream 5.0 Pro Edit (ByteDance)
High-fidelity image editing powered by Seedream 5.0 Pro, supporting instruction-based modifications with 1–10 reference images.

Qwen Image 2.0 (Alibaba)
High-performance image generation with sharp text rendering and realistic visuals. Optimized for stable, high-quality output at competitive pricing.

Qwen Image 3.0 (Alibaba)
High-quality text-to-image generation with strong prompt adherence and flexible composition control.

Qwen Image 3.0 Edit (Alibaba)
Instruction-based image editing with multi-image input support and precise visual refinement.

Qwen Image 3.0 Pro (Alibaba)
Professional text-to-image generation with knowledge-rich composition and multilingual text rendering.

Qwen Image 3.0 Pro Edit (Alibaba)
High-fidelity image editing with multi-image composition, instruction-based modifications, and consistent visual refinement.

Qwen Image Lora Edit (Alibaba)
Prompt-guided image editing for background changes, style updates, object edits, and polished production-ready visual refinements.

Wan 2.7 Image Pro (Alibaba)
Premium text-to-image generation from Alibaba's Wan 2.7 series, delivering enhanced visual quality with support for seven aspect ratios including 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.

Wan 2.7 Image Pro Edit (Alibaba)
High-fidelity image-to-image editing powered by Wan 2.7 Image Pro Edit, supporting instruction-based modifications with 1–9 reference images for precise visual refinement.

Wan 2.7 Image (Alibaba)
Cost-effective text-to-image generation from the Wan 2.7 series, ideal for high-volume creative workflows with flexible aspect ratio control.

Wan 2.7 Image Edit (Alibaba)
Instruction-based image editing with multi-image input support, enabling efficient visual modifications at competitive pricing.

Z Image (Alibaba)
Affordable text-to-image generation for marketing visuals, product imagery, social assets, and creative automation workflows.

Grok Imagine (xAI)
Image generation powered by xAI's Grok, delivering creative and diverse visual outputs.

Grok Imagine Edit (xAI)
Instruction-based image editing with Grok's understanding of complex natural language commands.

GPT Image 2 (OpenAI)
High-quality text-to-image generation with strong prompt adherence, flexible quality controls, and reliable typography rendering for production workflows.

GPT Image 2 Edit (OpenAI)
Prompt-driven image editing with support for multi-image inputs, context-aware modifications, and consistent visual preservation across complex edits.

GPT Image 2 Client (OpenAI)
OpenAI GPT Image 2 generation access through the client variant, offering the same core text-to-image workflow for teams standardizing on this route.

GPT Image 2 Edit Client (OpenAI)
Client-route access to GPT Image 2 editing, supporting instruction-based edits, multi-image composition, and flexible creative refinement workflows.

ChatGPT Images 2.5 (OpenAI)
Cost-effective text-to-image generation with flexible aspect ratios for product imagery, marketing assets, and creative workflows.

ChatGPT Images 2.5 Edit (OpenAI)
Instruction-based image editing with multiple reference images and flexible aspect ratios for visual refinement and composition.

ChatGPT Images 2.5 Client (OpenAI)
Affordable access to the same core ChatGPT Images 2.5 text-to-image workflow through the Client variant for creative applications.

ChatGPT Images 2.5 Edit Client (OpenAI)
Affordable access to the same core ChatGPT Images 2.5 editing workflow through the Client variant, supporting edits with 1–16 input images.

ChatGPT Images 2.5 Flare / Sunburst (OpenAI)
Text-to-image generation with flexible aspect ratios, resolution options, and quality controls.

ChatGPT Images 2.5 Flare Edit / Sunburst Edit (OpenAI)
Prompt-guided editing with 1–16 reference images and the same output controls.

Nano Banana 2.1 (Google)
Efficient text-to-image generation with improved prompt adherence, detailed visuals, and clear text rendering.

Nano Banana 2.1 Edit (Google)
Instruction-based image editing with up to 14 reference images for detailed, visually consistent refinements.

Video Generation Models

Veo 3.1 Text to Video (Google)
High-quality video generation from text prompts with advanced motion synthesis.

Veo 3.1 Image to Video (Google)
Transform static images into dynamic videos with sophisticated motion effects.

Veo 3.1 Fast Text to Video (Google)
Rapid video generation from text prompts, optimized for processing speed.

Veo 3.1 Fast Image to Video (Google)
Faster image-to-video conversion with reduced processing time.

Wan 2.6 Text to Video (Alibaba)
Advanced text-to-video synthesis delivering high-quality outputs.

Wan 2.6 Image to Video (Alibaba)
Sophisticated image-to-video transformation featuring complex motion and scene composition.

Wan 2.7 Text to Video (Alibaba)
Next-generation text-to-video synthesis with improved motion quality and prompt adherence over Wan 2.6.

Wan 2.7 Image to Video (Alibaba)
Advanced image-to-video transformation with enhanced scene dynamics and temporal consistency.

Wan 2.7 Lora (Alibaba)
Advanced Wan 2.7 animation workflows for turning still visuals into cinematic motion with prompt-guided camera movement and stable subject preservation.

Wan 2.7 Video Edit (Alibaba)
AI-powered video editing that applies text-guided modifications to existing video content.

MiniMax H3 (MiniMax)
Video generation family supporting text-to-video, start-and-end-frame image-to-video, and multimodal reference-to-video workflows with image, video, and audio inputs.

Happy Horse 1.0 (Alibaba)
High-quality video generation model supporting both text-to-video and image-to-video workflows, with flexible clip creation for creative and production use cases.

Seedance 1.5 Pro (ByteDance)
Native audio-visual sync video model with multilingual lip-sync capabilities and cinematic quality for professional video production.

Seedance 2.0 (ByteDance)
Next-generation audio-visual video model with standard and fast variants, supporting text-to-video, image-to-video, and reference-to-video generation modes.

Seedance 2.5 (ByteDance)
Video generation family supporting text-to-video, first-frame image-to-video with optional end-frame guidance, and reference-to-video workflows with video, image, and audio inputs.

Kling 3.0 (Kuaishou)
Efficient video generation with solid physical coherency and smooth scene transitions, ideal for dynamic content creation.

Kling 3.0 Turbo (Kuaishou)
Fast Kling video generation for text-to-video and image-to-video workflows with optional sound, designed for quick creative iteration and production use.

Kling Video O3 (Kuaishou)
Advanced reasoning-enhanced video model supporting text-to-video, image-to-video, reference-to-video, and video editing in both standard and pro tiers.

Vidu Q3 (Vidu)
High-quality video generation with turbo and pro variants, supporting text-to-video, image-to-video, and start-end frame control.

Pixverse C1 (PixVerse)
Text-to-video, first-frame image-to-video, and first-and-last-frame transition generation with flexible resolution and duration controls.

Pixverse V6 (PixVerse)
Text-to-video, image-to-video, transition, and video extend workflows with optional negative prompts and seeding on transition and extend variants.

Grok Imagine Video (xAI)
AI video generation by xAI, supporting both text-to-video and image-to-video creation.

Grok Imagine Video 1.5 (xAI)
Next-generation image-to-video animation by xAI with expanded aspect ratio support and flexible duration options.

Video Upscaler (Flaq AI)
Accessible video enhancement for improving the resolution and visual quality of existing footage through a simple video-to-video workflow.

Video Upscaler Pro (Flaq AI)
Quality-focused video enhancement for refining existing footage across professional media and production workflows.

Happy Horse 1.1 (Alibaba)
Versatile video generation for text-to-video, image-to-video, and reference-guided creative workflows.

Seedance 2.0 Mini (ByteDance)
Cost-effective video generation for efficient text-to-video, image-to-video, and reference-to-video workflows.

FLUX 3 (Black Forest Labs)
Video generation family supporting text-to-video, image-to-video, start-and-end-frame transitions, and video extension with native audio.

Wan 3.0 (Alibaba)
Video generation family supporting text-to-video, required start-and-end-frame image-to-video, prompt-guided video editing, and multimodal reference-to-video workflows.

Gemini Omni 1.1 Flash (Google)
Video generation family supporting text-to-video, required start-frame and optional end-frame image-to-video, source-video editing, and reference-to-video workflows with optional image and video inputs.

3D Generation Models

Tripo H3.1 Text to 3D (Tripo3D AI)
Generate a 3D model from a text prompt with configurable texture, PBR material, geometry, scale, and mesh settings.

Tripo H3.1 Image to 3D (Tripo3D AI)
Reconstruct a 3D model from one reference image with texture alignment and model orientation controls.

Tripo H3.1 Multiview to 3D (Tripo3D AI)
Build a 3D model from two to four ordered front, left, back, and right reference images.

Meshy 7 Text to 3D (Meshy)
Generate a 3D model from a text prompt with topology, polygon count, remesh, pose, and optional PBR texture controls.

Meshy 7 Image to 3D (Meshy)
Generate a 3D model from one reference image with configurable mesh, symmetry, pose, and texture settings.

Meshy 7 Multiview to 3D (Meshy)
Generate a 3D model from one to four reference images without a fixed view order, with mesh and texture controls.

Music Generation Models

Mureka 9.5 Generate BGM (Mureka)
Generate instrumental background music from a text description with selectable audio output formats.

Mureka 9.5 Generate Song (Mureka)
Turn supplied lyrics into songs with optional style guidance, vocal ID, and audio format selection.

Mureka 9.5 Prompt to Song (Mureka)
Generate complete songs with optional text descriptions, style tags, vocal ID, and audio format selection.

Mureka O2 Generate Song (Mureka)
Generate songs from supplied lyrics with optional style guidance, vocal ID, and audio format selection.

LLM Models

GPT 5.4 (OpenAI)
Fast and affordable OpenAI LLM API access for text-to-text, image-to-text, web search, and file analysis workflows.

GPT 5.5 (OpenAI)
Advanced OpenAI LLM access for reasoning, coding help, multimodal understanding, web-aware answers, and deep document analysis.

GPT 5.6 Sol (OpenAI)
Flagship OpenAI LLM access for advanced reasoning, coding, writing, multimodal understanding, web-aware answers, and professional file analysis workflows.

GPT 5.6 Terra (OpenAI)
Balanced OpenAI LLM access for dependable reasoning, writing, coding help, visual understanding, web research, and cost-effective document analysis.

GPT 5.6 Luna (OpenAI)
Fast and affordable OpenAI LLM access for high-throughput chat, writing, coding, image understanding, web search, and document analysis workflows.

Claude Sonnet 4.6 (Anthropic)
Balanced Claude LLM API for fast reasoning, writing, coding help, and file analysis with stable production access.

Claude Sonnet 5 (Anthropic)
Latest balanced Claude LLM API for fast reasoning, writing, coding help, and file analysis with stable production access.

Claude Opus 4.6 (Anthropic)
High-capability Claude Opus model for careful reasoning, complex writing, coding support, and document review workflows.

Claude Opus 4.7 (Anthropic)
Latest Claude Opus LLM for advanced reasoning, technical analysis, file understanding, and professional AI applications.

Claude Opus 4.8 (Anthropic)
Most capable Claude Opus model for complex reasoning, deep technical analysis, file and image understanding, and advanced AI workflows.

Claude Opus 5 (Anthropic)
Advanced Claude Opus LLM for demanding reasoning, writing, coding, and file or image analysis through text-to-text and file-analysis variants.

Claude Fable 5 (Anthropic)
Mythos-class Claude LLM for long-horizon reasoning, agentic coding, web-aware research, and file or image analysis through text-to-text, web search, and file analysis variants.

Gemini 3.5 Flash (Google)
Fast and efficient Google LLM for text generation, image understanding, and file analysis with low-latency responses.

Gemini 3.6 Flash (Google)
Efficient Google Flash LLM for text generation, image understanding, and file analysis, combining improved token efficiency with coding and agentic planning support.

Gemini 3.7 Flash (Google)
Google's latest Flash LLM for complex coding, agentic workflows, multi-step reasoning, image understanding, and file analysis through a highly cost-effective API configuration.

Qwen 3.7 (Alibaba)
Alibaba's reasoning LLM with Max and Plus tiers, supporting text generation and web-search-augmented answers.

Qwen 3.8 Max (Alibaba)
Max-tier Alibaba LLM for advanced text reasoning and web-search-augmented answers, with streaming and flexible generation controls.

Qwen Character (Alibaba)
Alibaba character roleplay LLMs with Plus and Flash tiers, supporting persona-driven chat, reusable profiles, memory-aware dialogue, and scalable storytelling workflows.

DeepSeek v4 (DeepSeek)
DeepSeek LLM access with Pro and Flash tiers for text generation, reasoning, coding help, and web-search-augmented answers for current-information workflows.

Kimi 2.7 (Moonshot AI)
Moonshot AI LLM access for text reasoning and image-to-text understanding, supporting writing, coding, visual analysis, OCR-style extraction, and multimodal assistant workflows.

GLM 5.2 (Z.ai)
Advanced Z.ai LLM for practical reasoning, coding help, structured text generation, and agent-oriented engineering workflows through a production-ready text-to-text API.

Grok 4 (xAI)
High-performance xAI LLM for text reasoning and image understanding with strong analytical capabilities.

Grok 4.5 (xAI)
Advanced xAI LLM for text generation, reasoning, coding assistance, and multimodal image understanding across analytical and conversational workflows.

Grok 4.6 (xAI)
Latest xAI LLM for advanced reasoning, coding, engineering, professional knowledge work, and image understanding through text-to-text and image-to-text variants.

Kimi K3 (Moonshot AI)
Moonshot AI text-only LLM access for long-horizon coding, reasoning, knowledge work, and scalable agent workflows.

GPT 6 Astra (OpenAI)
Advanced OpenAI LLM access for complex reasoning, coding, visual understanding, web research, and document analysis through text-to-text, image-to-text, web search, and file analysis variants.

Claude Fable 5.1 (Anthropic)
Advanced Claude LLM access for complex coding, knowledge work, web research, and file or image analysis through text-to-text, web search, and file analysis variants.

GPT 6 Sol (OpenAI)
OpenAI LLM access for writing, coding, conversation, image understanding, web research, and document analysis through text-to-text, image-to-text, web search, and file analysis variants.

GPT 6 Luna (OpenAI)
OpenAI LLM access for text generation, coding assistance, visual questions, online research, and file summaries through text-to-text, image-to-text, web search, and file analysis variants.

Claude Opus 5.5 (Anthropic)
Claude Opus LLM access for text reasoning, writing, coding, document review, and file or image analysis through text-to-text and file analysis variants.