Deploy high-performance APIs instantly. Choose from state-of-the-art models for text, vision, audio, and embeddings with transparent, low-cost pricing.
google/gemini-omni-flash-1-1
Gemini Omni 1.1 Flash is Google's multimodal model for AI video generation and editing. It offers greater creative control with 10-second context for scene extension, first and last frame control, fast 360p drafting, video references, and up to 4K output.
deepseek-ai/DeepSeek-V3.1
DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.
hailuo/02-image-to-video-standard
Hailuo 02 API is Minimax’s advanced AI video generation model that turns text or images into short, cinematic clips. It supports high-quality output up to 1080P, with realistic motion, physics simulation, and precise camera control.
MiniMax/Hailuo 2.3 Pro
Hailuo 2.3 is MiniMax’s high-fidelity AI video generation model designed to create realistic motion, expressive characters, and cinematic visuals. It supports both text-to-video and image-to-video, handling complex movements, lighting changes, and detailed facial expressions with stability and consistency.
ClarityAI/creative
ClarityAI/creative is an AI-powered image upscaler that enhances details, adds realism, and creatively modifies images to improve their quality and visual appeal.
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Maverick, a 17 billion parameter model with 128 experts
Qwen/Qwen3.5-27B
Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following. It features a 262K token context window (extensible to 1M), thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Best suited for production deployments and complex enterprise tasks requiring top-tier performance.
Wan-AI/Wan2.7-Image-Edit
Bleeding edge image model supporting generation and editing, text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following
deepseek-ai/DeepSeek-V3
DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.
black-forest-labs/FLUX-1-schnell
FLUX.1 [schnell] is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. This model offers cutting-edge output quality and competitive prompt following, matching the performance of closed source alternatives. Trained using latent adversarial diffusion distillation, FLUX.1 [schnell] can generate high-quality images in only 1 to 4 steps.
deepseek-ai/Janus-Pro-1B
Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder’s roles in understanding and generation, but also enhances the framework’s flexibility. Janus-Pro surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus-Pro make it a strong candidate for next-generation unified multimodal models.
black-forest-labs/FLUX-1-dev
FLUX.1-dev is a state-of-the-art 12 billion parameter rectified flow transformer developed by Black Forest Labs. This model excels in text-to-image generation, providing highly accurate and detailed outputs. It is particularly well-regarded for its ability to follow complex prompts and generate anatomically accurate images, especially with challenging details like hands and faces.
XiaomiMiMo/MiMo-V2.5-tts-voiceclone
Automatically convert input text into natural and fluent speech output. You can generate natural and vivid speech content by configuring parameters such as speech. Precisely replicate voices from audio samples to enable speech synthesis of any voice. style and voice.
BAAI/bge-base-en-v1.5
BGE embedding is a general Embedding Model. It is pre-trained using retromae and trained on large-scale pair data using contrastive learning. Note that the goal of pre-training is to reconstruct the text, and the pre-trained model cannot be used for similarity calculation directly, it needs to be fine-tuned
Qwen/Qwen3-TTS-VoiceDesign
Qwen3-TTS-VoiceDesign is a voice design variant of Qwen3-TTS by Alibaba's Qwen team. Instead of selecting from preset voices, you describe the voice you want in natural language — and the model generates speech in that voice. Key capabilities: - Natural language voice control — describe any voice with free text (e.g. "a deep male voice with a calm, authoritative presence", "a young cheerful female with a warm and friendly tone") - 10 languages — English, Chinese, Japanese, Korean, German, French, Russian, Spanish, Italian, Portuguese - Streaming support — real-time PCM streaming - Multiple output formats — WAV, MP3, FLAC, PCM Built on the same 1.7B parameter architecture as Qwen3-TTS, using discrete multi-codebook language modeling and a custom 12Hz acoustic tokenizer for high-quality end-to-end speech synthesis.
Bria/replace_background
Bria Background Generation allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use.
Wan-AI/Wan2.6-I2V
Turn any image into a video. Intelligent shot scheduling supports multi-shot storytelling, generating multi-shot narrative videos with consistent subjects, scenes, and atmosphere
ByteDance/Seedream-4
Seedream 4.0 is a SOTA multimodal image creation model built on leading architecture. It breaks through the boundaries of traditional text-to-image models by natively supporting text, single-image, and multi-image inputs. Users can freely combine text and images to achieve diverse creative modes within a single model—such as multi-image blending, image editing, and sequentially batch image generation, featuring subject consistency, making image creation more free and controllable.
anthropic/claude-sonnet-4-6
Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows.
bytedance/seedance-2-5
Seedance 2.5 is ByteDance’s next-generation AI video model, built for up to 30-second video generation, advanced multimodal reference control, precise local editing, and more flexible, production-ready creative workflows.
