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.

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.

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 是看似為 OpenAI 旗艦 GPT-6 Astra 模型家族的下一次迭代而設的內部或金絲雀代號。

Google ha annunciato ufficialmente Gemini 4 Carbon il 28 ottobre 2026. I suoi principali punti di forza sono la difesa avanzata della sicurezza informatica, la programmazione agentica continuativa, i compiti di ingegneria a lungo termine e un allineamento migliorato.

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.

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

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.

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.

Explore the Claude Haiku 5.5 API.

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

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.

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

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.

Hy-Image 3.5 Preview is Tencent Hunyuan's professional image-generation model focused on text-to-image, reference-guided generation, and multi-turn image editing.

From fast verification to cinematic output, billing is based on the generated video duration, selecting the appropriate resolution, and turning every generation into a planned creative investment activity rule

FLUX.2 [max] is the flagship, highest-quality variant of the FLUX.2 family from Black Forest Labs (BFL). It is positioned as a professional-grade text→image generation and image-editing model that focuses on maximal fidelity, prompt adherence, and editing consistency across characters, objects, lighting and color. BFL and partner registries describe FLUX.2 [max] as the top-tier FLUX.2 variant with features for multi-reference editing, grounded generation.

Vidu Q4 Preview is a preview-stage AI video generation model from Vidu, designed for image-to-video generation and reference-guided video creation.

GPT-6.1 Sol is an OpenAI model in the GPT-6.1 family designed for complex coding, computer use, and professional work.

Explore the Claude Fable 5.5 API.

coming soon

FLUX 2 DEV is the development-friendly version optimized for research, experimentation, and non-commercial applications. It provides developers with powerful image generation capabilities while maintaining a balance between quality and computational efficiency. Perfect for prototyping, academic research, and personal creative projects.

Eleven v4 is ElevenLabs' expressive speech-synthesis model, designed to generate natural-sounding speech with rich emotional delivery, contextual awareness, and strong voice consistency.