Explore the CometAPI model catalog

3.7 Flash delivers substantial improvements across software engineering, knowledge work, and web development workflows — with an introductory price of half the original 3.6 Flash cost per million tokens.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

The flagship model for code and everything else: agentic tool calling, minimal hallucinations, configurable reasoning.

minimax-h3 is a new video generation model designed for high-quality creative production. It delivers improved prompt understanding, stronger visual consistency, smoother motion, and more flexible reference-image control for cinematic video generation workflows.

seedance-2-5 is a next-generation audio-video joint generation model built for 30-second storytelling, with precise reference control and powerful editing capabilities.

GLM-5.3 is a next-generation open-source large language model optimized for complex coding, long-horizon tasks, and cybersecurity scenarios. It delivers significantly improved coding capabilities and agent performance compared with GLM-5.2.

FLUX 3 - Real World Models: Towards Multimodal Flow Models as the Backbone of Visual Intelligence.

Access to Claude Fable 5 has been restored. It brings 5th-generation intelligence to your most ambitious coding and professional work.

Claude Sonnet 5 API is live on CometAPI at $1.6 per million input tokens and $8 per million output tokens, 20 percent below Anthropic list price. One key gives you Claude Sonnet 5 plus 500+ models from OpenAI, Google, and ByteDance under all in one pricing and a single invoice. No seat fees. No monthly minimum. Pay only for what you use. Start free and make your first call in under five minutes.

Qwen3.8-Max is Alibaba Qwen’s flagship large language model designed for advanced reasoning, agentic workflows, multimodal understanding, and enterprise-scale AI applications.. It has 2.4T parameters, adopts the MoE architecture, supports switching between thinking and fast inference modes, can handle various content formats, and performs excellently in scenarios such as code engineering, professional office work, and complex logical reasoning, second only to Anthropic's Fable 5.

Start with GPT-5.6 Sol for complex reasoning and coding, choose GPT-5.6 Terra to balance intelligence and cost, or use GPT-5.6 Luna for cost-sensitive, high-volume workloads.

GPT Image 2 is openai state-of-the-art image generation model for fast, high-quality image generation and editing. It supports flexible image sizes and high-fidelity image inputs.

Claude Opus 5 is available today. It’s a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price.

Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at code generation, agentic execution, and spatial reasoning. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations.

Seedance 2.0 is ByteDance’s next-generation multimodal video foundation model focused on cinematic, multi-shot narrative video generation. Unlike single-shot text-to-video demos, Seedance 2.0 emphasizes reference-based control (images, short clips, audio), coherent character/style consistency across shots, and native audio/video synchronization — aiming to make AI video useful for professional creative and previsualization workflows.

Gemini 3.1 Flash Lite Image model is an efficiency expert in the image generation family, designed for ultra-low latency and cost-effective image generation and modification.

HappyHorse 1.1 is a multimodal video-generation model designed for professional content creation, advertising, short films, social media production, and storytelling. It extends the capabilities of HappyHorse 1.0—which gained significant attention after ranking highly in independent video-generation evaluations—with stronger scene coherence and improved visual fidelity.

Claude Opus 4.8 is a premium AI model designed for advanced reasoning, deep analysis, and high-quality content generation. It excels at handling complex instructions, long-context understanding, and sophisticated problem-solving across professional and technical domains.

Gemini 3.5 Flash is a high-speed AI model designed for fast response and efficient coding performance. It delivers significantly improved generation speed while maintaining strong reasoning ability, making it suitable for real-time applications and developer workflows.

Gemini 3.1 Pro is the next generation in the Gemini series of models, a suite of highly-capable, natively multimodal, reasoning models. Gemini 3 Pro is now Google’s most advanced model for complex tasks, and can comprehend vast datasets, challenging problems from different information sources, including text, audio, images, video, and entire code repositories

Kimi K3 is Kimi's flagship model, designed for long-range programming and end-to-end knowledge work, featuring 1M token context and leading-edge comprehensive intelligence.

Kimi K2.7 Code is Kimi's most intelligent coding model to date, reliably following instructions in long contexts and completing programming tasks with a higher success rate. It supports text, image, and video input, and only supports thought mode, dialogue, and agent tasks.

Happy Horse 1.0 — A high-quality audio-video generation model that supports text-to-video and image-to-video creation. It can generate synchronized visuals, audio, and lip movements, making it suitable for short films, advertising creatives, and product showcases.

Anthropic's most capable, widely released model, for the most demanding reasoning and long-horizon agentic work

Claude Opus 4.7 is a hybrid reasoning model designed specifically for frontier-level coding, AI agents, and complex multi-step professional work. Unlike lighter models (e.g., Sonnet or Haiku variants), Opus 4.7 prioritizes depth, consistency, and autonomy on the hardest tasks.

Minimax-m3 is a multimodal AI model designed for strong reasoning, natural conversation, and creative content generation. It provides balanced performance across text and visual understanding tasks, making it suitable for general-purpose AI applications.

GPT-5.5 Pro combines state-of-the-art intelligence, precision, and efficiency to tackle sophisticated challenges. From software development and data analysis to research and decision support, it delivers expert-level assistance with speed and consistency.

Model 5.5 is a next-generation AI model designed for stronger reasoning, faster responses, and improved accuracy across a wide range of tasks. It excels at understanding complex instructions, generating high-quality content, and assisting with coding, analysis, and problem-solving.

MiniMax-M2.7 offers the same top-tier intelligence as the standard version—including recursive self-evolution and expert-level office productivity—but is designed for applications requiring sub-second latency and high-speed token generation. Leveraging an enhanced inference backbone architecture, its output speed is 66% faster than the standard model (reaching 100 tps). It is the preferred choice for interactive programming assistants, real-time agent loop execution, and high-throughput enterprise pipelines with stringent completion time requirements.

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance.

GPT-5.4 Nano is an ultra-lightweight AI model built for maximum speed and efficiency. It is optimized for simple tasks, real-time interactions, and large-scale deployments where low latency and minimal resource consumption are essential.

GPT-5.4 Mini is a lightweight and efficient AI model optimized for speed and everyday productivity. It provides reliable conversational capabilities, content generation, and task assistance while maintaining low latency and resource usage.