1000+ AI models.
One API. Zero hassle.

Gemini 3.8 Flash API is available through a chat completions endpoint, released September 2, 2026 as Google's third Flash update in five weeks.

Please check back shortly or explore our other available AI models.

Seed-2.0-Code API is available through a chat completions endpoint.

Seed 2.1 Turbo API is available through a chat completions endpoint.

Sakana Namazu API is available through a chat completions endpoint.

Gemini 3.5 Flash Lite API is available through a chat completions endpoint.

Gemini 3.7 Flash API is available through a chat completions endpoint.

Grok 4.6 API is available through a chat completions endpoint.

Sharper reasoning, more honest output, and the best agentic performance the company has shipped.1

Gemini 3.5 Flash brings near-Pro reasoning at Flash speed. Explore specs, pricing, thinking levels.

Positioned at the very top of Alibaba's Qwen model family, Qwen3.7-Max isn't a general-purpose assistant with reasoning bolted on — reasoning is its foundation.

Claude Sonnet 5 API combines strong reasoning, adaptive thinking, and high-resolution vision for complex coding, agent loops, and long-document analysis.

Please check back shortly or explore our other available AI models.

Optimized for complex multi-step reasoning, long-context analysis, and agentic workflows. Supports tool use and extended context up to 1M tokens.

Sharper reasoning, more honest output, and the best agentic performance the company has shipped.

Gemini 3.5 Flash brings near-Pro reasoning at Flash speed. Explore specs, pricing, thinking levels.

For developers, researchers, and businesses that rely on fast-moving information and technical workflows.

This isn't a patch on GPT-5.4. It thinks faster, uses fewer tokens, and keeps going when problems get messy.

From end-to-end engineering tasks to navigating live software, GPT-5.5 closes the gap between "AI assistant" and "AI colleague."

Gemini 3 Flash Preview is Google’s fast multimodal LLM API for agents, coding, and docs with pro-level control.

With significant upgrades in reasoning, vision, coding, and long-context handling, GPT-5.2 delivers state-of-the-art performance across professional tasks.

It excels in software engineering and agentic workflows, supports advanced tool use and large context windowsl.

Gemini 3 Pro Image, also known as Nano Banana Pro, is Google DeepMind’s latest state-of-the-art text-to-image generation model.

It focuses on making the user experience more natural and the model’s reasoning behaviour more adaptive.

It is optimized for real-time dialog systems, analytics platforms, and visual assistant applications.

While it requires more computational resources and higher cost, the payoff is exceptional performance on complex and mission-critical tasks.

Alibaba's Qwen Max is a powerful multimodal AI with OpenAI-compatible API, notable for instruction-following stability.

Discover Qwen-Plus, Alibaba's advanced multilingual model designed for complex tasks and detailed analysis.

Meet Hy4 Preview — Tencent's next-generation open-source flagship model, built for long-horizon coding and agentic tool-use.

Meet Qwen3.8-Flash -- Alibaba's latest cost-efficient multimodal model.

Qwen Image 2.0 Pro is especially valuable for marketing teams, designers, and content creators who need production-grade assets rather than experimental visuals.

Nano Banana 2 Lite API delivers high-throughput text and image processing with native image generation — optimized for production workloads where speed and cost are the top constraints.

The model combines advanced multimodal training with diffusion-based image generation. This enables it to convert complex instructions into visually consistent outputs while preserving strong control over composition, typography, and layout.

GPT Image 1.5 is OpenAI’s image generation model, built to produce crisp images that closely follow your prompt and to support dependable editing and variations.

It delivers professional-grade image synthesis for commercial and creative applications with speed and efficiency at its core.

Meet Meta Muse Image Edit -- point it at an existing photo and describe the change.

Meet Meta Muse Image -- Meta's first image generation model from Meta Superintelligence Labs.

Meet Gemini 3 Pro Image Edit: describe the change and it edits your photo directly, supporting multi-turn edits and strong text rendering.

Meet Nano Banana Edit: describe the change and it edits your image directly, blending in up to 3 reference photos while keeping the rest of the scene intact.

Meet Gemini 2.5 Flash Image Edit: describe the change and it edits your photo directly, blending reference images while keeping subject and style consistent

Nano Banana API is available through a image generation endpoint.

Meet Nano Banana Pro Edit: point it at existing images and describe the change. It reasons through multi-step edits for studio-quality results.

Nano Banana Pro API is available through an image generation endpoint, built on Gemini 3 Pro for complex, multi-turn image editing workflows.

magen 4.0 Generate API delivers high-quality AI image generation with strong visual fidelity, detail, and text rendering capabilities.

Qwen Image 2.0 Pro is especially valuable for marketing teams, designers, and content creators who need production-grade assets rather than experimental visuals.

USO Image to Image API is available through an image generation endpoint.

FLUX.1 Dev API is available through an image generation endpoint.

FLUX.2 Klein 4B API is available through an image generation endpoint.

Nano Banana 2 API is available through an image generation endpoint.

Gemini 3 Pro Image Edit API is available through an image generation endpoint.

Flux Kontext Max API is available through an image generation endpoint.

Seedream 5.0 Lite Preview API is available through an image generation endpoint.

FLUX Virtual Try-On API is available through an image generation endpoint.

FLUX.2 Pro Preview API is available through an image generation endpoint.

FLUX.2 Flex API is available through an image generation endpoint.

Wan 2.7 Pro Image API is available through an image generation endpoint.

Flux Kontext Pro API is available through an image generation endpoint.

FLUX.1 Fill API is available through an image generation endpoint.

FLUX Outpainting API is available through an image generation endpoint.

TripoSR API is available through an image generation endpoint.

FLUX Erase API is available through an image generation endpoint.

Hunyuan Image V3 API is available through an image generation endpoint.

FLUX.2 Klein 9B API is available through an image generation endpoint.

Stable Diffusion v3 Medium API is available through an image generation endpoint.

SwitchX Image to Image API is available through an image generation endpoint.

Stable Diffusion v3.5 Large API is available through an image generation endpoint.

Wan 3.0 Video API is available through a video generation endpoint.

FLUX 3 Video (Text to Video / Image to Video) API is available through a video generation endpoint.

Seedance 2.5 API is available through a video generation endpoint, priced per token based on resolution, frame rate, and duration.

Gemini Omni Flash Preview API enables flexible video creation from text, images, and existing video clips — with durations up to 10 seconds and conversational multi-turn editing.

The model processes inputs to generate up to 8-second video clips at 720p resolution, embedding natural camera movements, smooth frame transitions, and native audio tracks.

The model produces fully synchronized audiovisual content, with support for various aspect ratios and high-definition output.

OpenAI’s Sora 2 is a next-generation AI model specialized in generating high-quality, photorealistic videos directly from image inputs.

With dedicated Text-to-Video and Image-to-Video APIs, it offers flexible entry points for both concept-driven storytelling and visual iteration.

MiniMax H3 Max API is available through a video generation endpoint.

Meet Gemini Omni 1.1 Flash -- Google's generally available conversational video model with scene extension and resolution control from 360p to 4K.

FLUX 3 Video Draft (Video to Video) API is available through a video generation endpoint.

FLUX 3 Video Draft (Text to Video / Image to Video) API is available through a video generation endpoint.

FLUX 3 Video (Video to Video) API is available through a video generation endpoint.

Seedance 2.0 API is available through a video generation endpoint.

Wan 2.7 Reference to Video API is available through a video generation endpoint.

Kling 3.0 Turbo Pro Text to Video API is available through a video generation endpoint.

Kling 3.0 Standard Image to Video API is available through a video generation endpoint.

Kling 2.0 Master Text to Video API is available through a video generation endpoint.

Kling Avatar Standard API is available through a video generation endpoint.

Kling 1.0 Standard Text to Video API is available through a video generation endpoint.

Kling 1.6 Pro Image to Video API is available through a video generation endpoint.

Veo 3 Text to Video API is available through a video generation endpoint.

Magic Video to Video API is available through a video generation endpoint.

Kling 3.0 Turbo Pro Image to Video API is available through a video generation endpoint.

Kling 3.0 Pro Text to Video API is available through a video generation endpoint.

Kling 2.6 Motion Control API is available through a video generation endpoint.

Kling 2.5 Turbo Pro Text to Video API is available through a video generation endpoint.

Kling 2.0 Master Image to Video API is available through a video generation endpoint.

Kling Avatar Professional API is available through a video generation endpoint.

Kling 2.1 Standard Image to Video API is available through a video generation endpoint.

Kling 1.0 Standard Image to Video API is available through a video generation endpoint.

Kling 1.6 Standard Text to Video API is available through a video generation endpoint.

Kling 1.5 Pro Text to Video API is available through a video generation endpoint.

Wan 2.6 Image to Video Flash API is available through a video generation endpoint.

Kling 3.0 Standard Turbo Text to Video API is available through a video generation endpoint.

Discover Qwen2.5 Coder 32B Instruct: An open-source coding LLM for efficient code solutions.

Access Replit's 2.7B parameter code completion model, along with 100+ AI Models. 20 Supported programming languages in your hands.

CodeGen2-16B: A colossal language model developed by Salesforce AI Research for advanced program synthesis tasks.

CodeGen2-7B API delivers AI-powered code generation, helping developers create, complete, and improve code efficiently.

Explore the power of StarCoder API, a 15.5B parameter model, ideal for generating code across 80+ programming languages with unparalleled depth.

SQLCoder API converts natural language queries into precise SQL commands, helping developers automate database query generation.

Phind Code LLaMA v2 (34B) API transforms coding by automating generation, debugging, and translating code across multiple languages.

WizardCoder Python v1.0 34B API enhances Python development with AI-powered code generation, debugging, and optimization.

Elevate your coding with Code Llama Instruct (34B) API, an AI model specialized in following complex instructions and generating precise code. Ideal for developers seeking high-level programming assistance.

Elevate your coding experience with Code Llama Instruct (7B) API. This AI model provides precise code generation and instructions compliance, making coding more efficient and accessible for developers of all levels.

The Code Llama Python (13B) API is a high-performance AI model designed to automate and enhance Python programming tasks. With 13 billion parameters, it excels in generating code, debugging, and providing programming insights.

Transform your coding processes with Code Llama Instruct (13B) API, an AI model specialized in understanding and executing programming instructions. With 13 billion parameters, it offers nuanced code generation and problem-solving capabilities, setting new standards in AI-assisted development.

Experience next-level code generation with Code Llama Python (34B) API. This model offers deeper insights and more complex code solutions, enhancing your programming projects with AI efficiency.

Unlock the power of AI in your coding projects with Code Llama Python (7B) API. This model accelerates code writing, debugs, and suggests optimizations effortlessly.

Empower your development with Deepseek Coder Instruct (33B) API, a state-of-the-art AI model with 33 billion parameters designed for coding instruction and automation.

Elevate your coding with Code Llama (70B) API. This massive open source model is designed to understand and generate code across multiple programming languages.

Unlock the full potential of AI in coding with Code Llama Python (70B) API. This 70 billion parameter model specializes in understanding and generating Python code, offering unparalleled assistance in software development.

CodeLlama-70B-Instruct API: Meta's AI model tailored for code tasks, excelling in code completion and chatbot applications. Suitable for research and commercial use.

Lyria 2 API is available through the AIMLAPI endpoint.

Whisper Tiny API is available through a speech-to-text endpoint.

Nova-2 Phonecall API is available through a speech-to-text endpoint.

Nova-2 Drive Thru API is available through a speech-to-text endpoint.

Whisper Small API is available through a speech-to-text endpoint.

Nova-2 Meeting API is available through a speech-to-text endpoint.

Nova-2 Conversational AI API is available through a speech-to-text endpoint.

Speech 2.5 Turbo Preview API is available through a text-to-speech endpoint.

Whisper Medium API is available through a speech-to-text endpoint.

Nova-2 Medical API is available through a speech-to-text endpoint.

Nova-2 Automotive API is available through a speech-to-text endpoint.

Whisper Base API is available through a speech-to-text endpoint.

Speech 2.5 HD Preview API is available through a text-to-speech endpoint.

Nova-2 Video API is available through a speech-to-text endpoint.

Nova-2 Finance API is available through a speech-to-text endpoint.

Nova-2 Voicemail API is available through a speech-to-text endpoint.

Nova-2 General API is available through a speech-to-text endpoint.

Seed Audio 1.0 API generates high-quality speech, sound effects, and custom-timbre audio from text and reference inputs at a low per-second price.

Optimized for healthcare environments: accurately recognizes drug names, diagnoses, procedures, and medical jargon in real-time and batch transcription.

Supports streaming and batch transcription, automatic language detection, speaker diarization, and advanced audio intelligence for multilingual workflows.

Supports streaming transcription, speaker diarization, smart formatting, and intent/topic detection for monolingual English workflows.

MAI-Voice-2 API is Microsoft's advanced text-to-speech model built on Azure AI Speech for natural, expressive voice generation.

MAI-Transcribe 1.5 API is Microsoft's multilingual speech recognition model built on Azure AI Speech for accurate transcription.

It enables creators and developers to generate high-quality cover versions with customizable vocals, instrumentation, and production.

It moves beyond short clips or loops and focuses on delivering coherent, multi-part compositions with vocals, arrangement, and progression.

It focuses on delivering speech that feels polished and production-ready, with attention to detail that goes beyond standard TTS systems.

It focuses on delivering natural, expressive speech with minimal delay, making it a strong fit for interactive environments where users expect immediate, human-like responses.

An 8.8‑billion‑parameter transformer model that speaks with near‑human subtlety.

For developers building responsive AI characters, this model offers the best trade-off of cost, speed, and quality in Inworld's lineup.

Inworld TTS-1-Max is a high-fidelity, transformer-based neural text-to-speech model optimized for interactive and emotionally expressive voice synthesis.

A next-generation neural text-to-speech (TTS) model developed by Inworld AI, engineered specifically for dynamic voice applications.

Designed for developers and creative teams, it produces complete songs that feel composed and arranged rather than mechanically generated.

Its advanced pretraining and reinforcement learning techniques make it ideal for real-time transcription in voice agents and call centers.

GPT-4o Transcribe API provides accurate speech-to-text transcription for voice agents, conversations, and real-time audio applications.

The Turbo version is finely optimized for real-time applications requiring expressive voices with minimal delay.

The model is optimized for high-definition audio output, supporting studio-grade prosody, breath control, and smooth phrasing.

Suno AI API generates realistic music from text prompts, supporting diverse genres, languages, and seamless integration into applications.

Turns text into vectors for semantic search, RAG, and text analysis workflows.

Turns text into vectors for search, clustering, and classification — with stronger retrieval quality than v3.

Voyage finance 2 API is available through an embeddings endpoint.

Voyage Multilingual 2 API is available through an embeddings endpoint.

Voyage code 2 API is available through an embeddings endpoint.

Voyage law 2 API is available through an embeddings endpoint.

Voyage 2 API is available through an embeddings endpoint.

Voyage Large 2 API is available through an embeddings endpoint.

Qwen Text Embedding v4 is a state-of-the-art multilingual embedding model optimized for semantic search and retrieval tasks.

Built on Qwen3 foundations, it prioritizes long-context understanding and semantic accuracy for real-world applications.

Discover the textembedding-gecko@001 model API: features, technical specifications, usage guidelines, and ethical considerations for developers.

Explore Textembedding-gecko@003 API, a powerful text embedding model by Google, designed for diverse NLP applications and high performance.

Explore the textembedding-gecko-multilingual@001 model API, its architecture, training data, performance, and applications in NLP tasks.

Discover Text-multilingual-embedding-002 API, a powerful model for multilingual text embeddings, enhancing NLP applications across languages.

Voyage Large 2 Instruct API: A top-performing, instruction-tuned text embedding model for retrieval, classification, and clustering tasks.

text-embedding-ada-002 API delivers consistent text embeddings, ideal for search, clustering, and recommendation applications at an affordable price.

Text-embedding-3-large API provides top-tier text embeddings with customizable dimensions, delivering exceptional accuracy for complex applications.

text-embedding-3-small API enhances text representation, offering better accuracy and cost-efficiency compared to its predecessor, text-embedding-ada-002.

Generate detailed language embeddings with BAAI-Bge-Base-1p5 API for accurate linguistic analysis and AI applications.

Unlock NLP with BERT Base Uncased API for powerful language embeddings, enabling deeper text understanding and accurate language analysis.

Sentence-BERT API creates sentence embeddings that capture semantic meaning for search, similarity, and natural language applications.

M2-BERT-Retrieval-32k API provides efficient semantic search and information retrieval with support for large 32K-token contexts.

UAE-Large-V1 API generates high-quality text embeddings for semantic search, retrieval, clustering, and natural language understanding.

Elevate language processing with BGE-Large-EN-v1.5 API, a state-of-the-art embedding model for accurate language understanding and analysis.

Elevate your search capabilities with M2-BERT-Retrieval-8k, an AI model optimized for fast and accurate information retrieval.

Enhance your search capabilities with M2-BERT-Retrieval-2K API, an AI model optimized for rapid and accurate information retrieval in smaller datasets.

Discover Microsoft’s WizardLM 2-8 (22B), an advanced language model optimized for multilingual conversations and complex reasoning tasks with high efficiency.

Access Llama-3 (8B) API along with 100+ AI Models. LLama-3 8B is an optimized, open-source language model excelling in dialogue, reasoning, and code generation.

Access Meta's Llama-3 (70B) AI along with other 100+ other AI models with our API.

Dive into the world of enhanced language processing with StableLM-Base-Alpha API, boasting up to 7 billion parameters for superior text generation.

Discover FLAN-T5 XL (3B) API, a T5 model enhanced by fine-tuning across more than 1,000 diverse tasks.

Explore the capabilities of GPT-NeoX-20B API for generating complex, context-aware text across a multitude of domains.

Mixtral 8x22B API, a pioneering AI model with 176 billion parameters, offers unparalleled language processing capabilities.

Experience efficient, AI-powered content moderation to ensure respectful, safe digital environments with GPT-JT-Moderation (6B) API.

Falcon-7B API offers unmatched language understanding and generation, leveraging 1,500B tokens and cutting-edge technology, under a flexible Apache 2.0 license.

The AI model from RedPajama-INCITE (3B) API utilizes advanced technology to analyze data and provide valuable insights for business decision-making.

Falcon 40B API leads in natural language generation, offering multilingual support and efficient, scalable AI-driven text creation.

Qwen (7B) API is a state-of-the-art language model that combines advanced performance with remarkable efficiency, making it a top choice for developers and enterprises.

RedPajama-INCITE Instruct 3B API provides efficient instruction-following and text generation for AI applications.

RedPajama-INCITE 7B API is an adaptable language model for customizable text generation and accurate AI-powered results.

RedPajama-INCITE (7B) API is a highly adaptable and customizable AI model that delivers accurate and relevant results, making it an invaluable resource for a wide range of applications.

NexusRaven 13B API supports data-driven decision-making with AI-powered text generation and reasoning capabilities.

Discover the versatility of 01-ai Yi Base (6B) API, an AI model adept in text generation, language understanding, and data analysis.

Unleash the potential of AI with LLaMA-2 (13B) API, a model boasting 13 billion parameters, designed for comprehensive data analysis and deep learning.

Harness the power of LLaMA-2-32K (7B) API, an AI model with 7 billion parameters and 32,000 token support.

LLaMA-2 (70B) API is a powerful language model for advanced text generation, reasoning, and natural language processing across diverse applications.

StripedHyena Hessian 7B API is an AI model designed for data analysis, pattern recognition, and complex language tasks.

Qwen 1.5 (1.8B), a beta version of Qwen2, excels in text generation, chatbots, and content moderation with its transformer-based architecture. It outperforms competitors in benchmarks, offering multilingual support and advanced capabilities across various domains.

Qwen 1.5 (0.5B) API is a lightweight language model for efficient text generation and conversational AI applications.

Microsoft Phi-2 API is a compact language model designed for efficient reasoning, text generation, and AI development tasks.

wen 1.5 (4B) API delivers efficient, high-quality dialogue with 4 billion parameters for streamlined conversational AI applications.

Discover unparalleled conversational AI with Qwen 1.5 (14B) API. Empower your applications with deep, nuanced interactions, thanks to its 14 billion parameter architecture.

Qwen 1.5 (7B) API delivers intelligent conversational AI with 7 billion parameters for nuanced, engaging interactions.

Qwen 1.5-72B: Transformer-based language model with multilingual support, 32K context, and strong performance in text completion and reasoning.

Gemma (7B) created an AI model that uses machine learning to predict customer behavior and preferences for personalized recommendations.

The AI model Mixtral-8x7B v0.1 API is a cutting-edge, advanced system designed to accurately analyze and process data in multiple domains.

Gemma's AI model utilizes deep learning techniques to accurately predict outcomes in a wide range of industries.

StripedHyena Nous 7B API uses advanced machine learning to analyze and interpret complex datasets and text.