Explore the CometAPI model catalog

Text Generation

AUTO

auto

CometAPI Auto API is an intelligent model routing feature that allows developers to access the appropriate AI model without specifying a specific model ID for each request.

Gemini 4 Hydrogen is Google's efficiency-oriented model in the Gemini 4 family, announced on November 12, 2026.

Seedance 2.5 Flash is ByteDance's speed- and cost-optimized variant of Seedance 2.5, designed for faster video generation and high-volume creative workflows.

Explore the Gemini 4 Krypton API.

Explore the Muse Mmber API.

Explore the Seedream 5.5 API.

Qwen4 Max is Alibaba's next-generation flagship model in the Qwen family. It combines text generation, deep reasoning, image and video understanding, tool calling, and structured outputs

Claude Fable 5.2 is Anthropic's advanced AI model for complex, open-ended technical work that requires sustained reasoning, planning, and execution across multiple steps.

MiniMax H3Image is an emerging AI image-generation model reportedly appearing in early access on Hailuo AI

GPT-6.2 Sol is reportedly the next iteration of OpenAI’s Sol line

GPT Image 2.6 is OpenAI's image generation and editing model family, designed for professional visual creation, precise image manipulation, and more controllable creative workflows.

GPT-6 Luna (gpt-6-luna) is OpenAI's efficient GPT-6 model for focused, high-volume workloads. OpenAI positions Luna below GPT-6 Sol in the GPT-6 family, emphasizing efficiency, repeatability, and cost-sensitive production use.

On October 17, 2026, the company released **DeepSeek-V4.1-Flash-1017**, a targeted update to its V4.1-Flash model (originally launched September 10, 2026). Marketed as delivering substantial improvements in reasoning, coding, agentic capabilities, and visual understanding—while reducing task execution time and output length—this checkpoint is positioned as DeepSeek’s most powerful efficient model to date for real-world agent and coding workloads.

The deepseek-v4-flash-vision-exp model accepts images alongside text, so you can ask the model to describe pictures, read text from screenshots, analyze charts, and more.Supported image formats: JPEG, PNG, GIF, and WebP. The format is detected from the actual file content, not from the file name or the declared MIME type.

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.

deepseek-r2 coming soon

Gemini 4 Carbon is Google's reasoning model for complex software engineering, scientific reasoning, and sustained agent workflows. It is available on CometAPI through the native Gemini API and OpenAI-compatible Chat API.

Tencent Hy4 is a next-generation large language model developed by Tencent's Hunyuan team, designed for complex reasoning, agentic workflows, software engineering, and real-world productivity tasks.

GPT-6.2 Astra is the internal or canary designation for what appears to be the next iteration of OpenAI’s flagship GPT-6 Astra model family

GPT-6.1 Terra is a fast, cost-efficient OpenAI model designed to combine visual understanding, precise computer use, and clear writing.

Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are two serving variants of Moonshot AI’s flagship K3.1 Pro multimodal reasoning model.

Explore the DeepSeek V4.1 Pro API.

Muse Wonder Full is a frontier AI model developed by Meta for complex coding and professional workflows that require planning, sustained reasoning, tool use, and error recovery.

Muse Wonder is Meta's agent-oriented AI model for tasks that require more than a single response.

Wan 3.0 Prime is Alibaba Cloud Model Studio's speed-optimized version of the Wan 3.0 video-generation model.

Gemini Nano Banana 2.1 is Google's high-efficiency image-generation and conversational-editing model. It updates Nano Banana 2 while retaining Flash-level efficiency and adds improvements in visual quality, prompt adherence, multi-turn character consistency, text rendering, and infographic layout.

Explore the Claude Haiku 5.5 API.

FLUX 3 Image is designed for creators and developers who need more control over the structure of a generated image than a simple text prompt may provide.

Gemini 4 Argon is the flagship model anchoring Google's Gemini 4 generation.

Discover DeepSeek Flash, a 552B multimodal MoE model with 1M-token context, adjustable reasoning, benchmark results, pricing, and CometAPI access.

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.

Qwen-Image-3.0 is Alibaba Qwen's third-generation image generation model, designed to make AI-generated images more useful for real-world creative and design workflows rather than focusing only on visual aesthetics.