探索 CometAPI 模型目錄

Text 生成

AUTO

auto

CometAPI Auto API 是一項智慧型模型路由功能，讓開發人員無需為每次請求指定特定的模型 ID，即可存取合適的 AI 模型。

探索 GPT-6 Sol API。

Claude Opus 5.2 may be undergoing limited testing in Claude Code. Here is what the leaks claim, what remains unverified, and how CometAPI access would work after release.

GPT-6 Astra, the flagship model for complex reasoning and coding. Choose GPT-5.6 Terra to balance intelligence and cost,

探索 Gemini 4 API。

Gemini 3.8 Flash is a new-generation lightweight Gemini model, with the goal of achieving a better balance among speed, cost, and coding capability.

claude-fable-5-1 為長時間執行的智能體提供下一代智能

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

OpenAI 最強大的圖像生成模型，具備跨多語言近乎完美的文字渲染、最高可達 4K 解析度，以及由推理驅動的 Thinking Mode。專為對準確性、速度與符合品牌調性的視覺輸出有嚴格要求的生產級工作流程而打造。

GLM-5.3-Flash is the first native multimodal model in the GLM-5 series, delivering stronger intelligence than GLM-5.2 while maintaining an exceptionally cost-efficient architecture.

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

探索 gpt-oss-20b(free) API。

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

Gemini 3.1 Flash Lite Image model 是圖像生成系列中的效率專家，專為超低延遲與具成本效益的圖像生成與修改而設計。

HappyHorse 1.1 是一款多模態影片生成模型，專為專業內容製作、廣告、短片、社群媒體製作與故事創作而設計。它在 HappyHorse 1.0 的基礎上擴展了能力——HappyHorse 1.0 因在獨立的影片生成評測中名列前茅而廣受關注——並具備更強的場景連貫性與更佳的視覺保真度。

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.

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.

探索 GPT Image 2.5(sunburst) API。

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.

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.

Seedance 2.0 是 ByteDance 面向電影級、多鏡頭敘事影片生成的新一代多模態影片基礎模型。不同於單鏡頭的文字轉影片示範，Seedance 2.0 強調基於參考的控制（圖像、短片段、音訊）、角色與風格在跨鏡頭間的連貫與一致性，以及原生的聲畫同步——旨在讓 AI 影片切實服務於專業創作與前期預視工作流程。

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.

GPT-Realtime-2 is our most capable realtime voice model. It supports speech-to-speech interactions with configurable reasoning effort, stronger instruction following, and more reliable tool use for complex voice-agent workflows

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.

seedance-2-0

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.

The best voice model for audio in, audio out.

OpenAI 最強大的模型，專為最艱鉅的任務與長時間運行的代理式工作流程打造。GPT-5.5 Pro 在複雜程式設計、電腦操作、深度研究、資料分析與科學推理方面表現卓越—以 GPT-5.4 的延遲並具備更高的 token 效率，提供前沿級智能。非常適合對準確性與自主任務執行提出最高標準要求的企業與專業應用場景。

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.

GPT-5.3-Codex is optimized for agentic coding tasks in Codex or similar environments. GPT-5.3-Codex supports low, medium, high, and xhigh reasoning effort settings.

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 Image 2 ALL is a comprehensive image generation model designed to handle a wide range of creative and professional visual tasks. It combines high-quality image creation, advanced prompt understanding, and versatile style support to deliver exceptional results across diverse use cases.