Endringslogg

Systemmelding

Comet Update

🌟 2026-02-13

🎉 CometAPI Adds minimax-m2.5! 🎉

🔹 minimax-m2.5

The world's first production-grade model natively designed for Agents. Its Coding & Agentic performance benchmarks directly against Claude Opus 4.6.

  • Full-Stack Coding: Supports PC, App, and cross-platform application development.
  • Office SOTA: Leads the industry in core productivity scenarios such as advanced Excel processing, in-depth research, and PPT generation.

📚 Developer Documentation

🌟 2026-02-12

🎉 CometAPI Adds glm-5! 🎉

🔹 glm-5

Zhipu's new generation flagship base model, built for Agentic Engineering. It provides reliable productivity in complex system engineering and long-horizon Agent tasks; the usage experience in real-world coding scenarios approaches Claude Opus 4.5.

📚 Developer Documentation

🌟 2026-02-06

🚀 cometapi: Supports Claude Opus 4.6

✨ Core Features

  • Ultimate Intelligence Model: Claude Opus 4.6 delivers world-class programming and logical reasoning experience.
  • Dual Protocol Support: Perfectly compatible with OpenAI Standard Format and Anthropic Native Format.

🔌 Call Parameters

  • Model Names: claude-opus-4-6 ,cometapi-opus-4-6

📚 Developer Documentation

⚠️ 2026-02-05

🔄 CometAPI: chatgpt-4o-latest Deprecation Notice

✨ Change Details

  • Upcoming Shutdown: In accordance with the official schedule, chatgpt-4o-latest will be discontinued on Feb 17, 2026.
  • Migration: Please migrate to the latest flagship GPT-5.2 Series. We recommend gpt-5.2 for most use cases or gpt-5.2-chat-latest for the newest chat improvements.

🔌 Recommended Models

  • Model Names: gpt-5.2 , gpt-5.2-chat-latest

📚 Developer Documentation

⚠️ 2026-02-04 🔄 CometAPI: Doubao Model Update Notice ✨ Change Details

Legacy Deprecation: In compliance with official policy, the Doubao 1.5 / 1.6 Series have been discontinued.

Migration: Please switch to doubao-seed-1.8.

🔌 Recommended Model

Model Name: doubao-seed-1.8

📚 Developer Documentation

🌟 2026-01-28

🦌 Comet Update: Qwen3 Flagship / Kimi Long Context / OCR v2

🚀 New Models

  • qwen3-max-2026-01-23 (General Flagship)

  • The strongest snapshot of the Qwen3 series, introducing a Deep Reasoning module. Improves complex logic deduction and code refactoring capabilities by 40%. Ideal for research assistance and system-level instructions.

  • kimi-k2.5 (Long Context)

  • Kimi's smartest model to date. Built on a native multimodal architecture, supporting both vision and text inputs simultaneously.

  • deepseek-ocr-2 (Visual Extraction)

  • Specialized in handwriting and complex table restoration. Eliminates hallucinations in dense formulas and supports direct Markdown/JSON structured output.

  • 👉 API Docs

🌟 2026-01-19

🎉 Major Update! CometAPI Now Supports gpt-5.2-codex ！ 🎉

🚀 Available Models & Usage Guide

🔹 gpt-5.2-codex (For Professional Code Tasks)

  • Model ID:gpt-5.2-codex
  • Description: Optimized for coding tasks like code generation, completion, and analysis to leverage its best-in-class coding capabilities.
  • Required Endpoint: /v1/responses (Note: This endpoint must be used for this model.)
  • Documentation: 👉 Check out the Responses API documentation

2026-01-08

1️⃣ Doubao-Seed-1.8 (Multimodal)

Deep reasoning and powerful multimodal understanding

  • Model ID: doubao-seed-1-8-251228
  • Endpoint: /v1/chat/completions
  • 👉 API Docs

2️⃣ Kling 2.6 (Video Generation)

Cinematic quality with native audio synthesis and audio-visual synchronization

  • Model ID: kling-v2-6
  • Features: Text/Image-to-Video | 5s/10s | Multiple Audio Modes
  • 👉 API Docs

📅 2026-01-04

🌟 CometAPI Major Release: FLUX 2 MAX is Now Live 🎉

🚀 Multiple Access Methods Now Available:

🔹 Compatible Format

🔹 BFL Native Format

💡 FLUX 2 MAX Core Highlights: 🎯 Ultimate Complex Editing Capabilities 🛍️ E-commerce Photography Revolution: From 0 to 1 🎬 Cinematic-Grade Keyframe Generation 🎨 Hex-Code Level Color Control 👓 Single-Image 3D View Generation 🌐 Real-Time Info Driven Creation

🌟 2025-12-17

🔥 Comet New Release: Gemini 3 Flash — lightweight, efficient multimodal model & GPT-Image-1.5 — state-of-the-art image generation model

1️⃣ Multimodal Conversation Model

  • gemini-3-flash ⚡️ Key Features:
  • Fast response
  • Ultra-low latency
  • Multimodal understanding and generation
  • Lightweight and efficient, ideal for real-time scenarios

✅ Recommended Endpoint:

  • /v1/chat/completions

👉 Integration Guide

1️⃣ Image Generation Model

  • gpt-image-1.5 ⚡️ Key Features:
  • Ultra-fast generation
  • Strong prompt understanding
  • High-fidelity image quality
  • Stable faces and identity consistency
    ✅ Recommended Endpoint:
  • /v1/images/generations

👉 Integration Guide

🌟 2025-12-12

🔥 Comet New Release: GPT-5.2 Series

⚡️ Key Features: Comprehensive performance upgrade! Pro version delivers ultimate logical reasoning & stability; Chat Latest features an up-to-date knowledge base.

💎 New Models & Integration Guide:

1️⃣ Standard / Latest

2️⃣ Pro Version

  • gpt-5.2-pro ⚠️ Required Endpoint: /v1/responses (MUST use this endpoint) 👉 Responses API Docs

🚀 Fully available now. Happy coding!

🌟 2025-12-04

✨ New Models

  • deepseek-v3.2 - Official stable version now available
    • Model ID: deepseek-v3.2
  • ByteDance Seedream 4.5 - Advanced image generation
  • Sora - Now supports character creation

🔄 Model Deprecation - Action Required

⚠️ gpt-4o-realtime-preview-2024-10-01 will be deprecated on December 3, 2025.

  • Please migrate to: gpt-realtime
  • New features: Improved reliability, better tool calling, enhanced interruption handling, and 2 new voices (Cedar & Marin).

🌟 2025-11-27

🚨 [URGENT] Announcement: Deprecation and Upgrade of Claude 3 Series & Gemini 2.5 Preview Models

According to the latest official notifications from Anthropic and Google, our platform will officially deprecate the legacy Claude 3 Series and Gemini 2.5 Preview Series Seriesmodels on December 1st at 00:00. To avoid API call failures, please ensure you switch to the following Model IDs before the deadline:

1. Claude Series (Upgrade to 4.5)

Version Please replace with new Model ID
Intelligent (Sonnet) claude-sonnet-4-5-20250929
Most Powerful (Opus) claude-opus-4-5-20251101
Fastest (Haiku) claude-haiku-4-5-20251001

2. Gemini Series (Upgrade to 2.5 Stable / 3.0 Preview)

Version Please replace with new Model ID
Standard (Flash) gemini-2.5-flash
Image Enhanced gemini-2.5-flash-image or gemini-3-pro-image-preview
Professional (Pro) gemini-2.5-pro or gemini-3-pro-preview

⚠️ Note: The old models will cease to function immediately after December 1st. Please migrate as soon as possible to ensure business continuity.

📅 2025-11-26

🌟 CometAPI Major Launch: FLUX.2 Series - Limited Time Offer 🎉

🚀 Now Supporting Asynchronous Format Models: 🔹 black-forest-labs/flux-2-pro 🔹 black-forest-labs/flux-2-dev 🔹 black-forest-labs/flux-2-flex

💰 Limited Time Promotion: Lower than Replicate Official Pricing!

💡 FLUX.2 Key Highlights: 🖼️ Multi-Reference Editing: Supports 8-10 reference images to satisfy complex character generation needs. 📸 Ultra-High Quality: Up to 4MP resolution for ultimate natural realism. ⚡ Flexible Selection: • Pro: Designed for high-efficiency production and fast delivery. • Flex: Maximizes image quality with adjustable parameters. • Dev: Developer-friendly optimization.

👇 Start Building Now Create Predictions - API Doc

🌟 2025-11-25 🎉 CometAPI Launches Claude Opus 4.5 Series!

🚀 Available Models: 🔹 claude-opus-4-5-20251101-thinking 🔹 claude-opus-4-5-20251101 🔹 cometapi-opus-4-5-20251101-thinking 🔹 cometapi-opus-4-5-20251101

💡 Why Claude Opus 4.5? Top choice for intensive reasoning, code automation, and complex Agent systems.

✨ Key Highlights: 🧠 Superior Reasoning: Handles complex logic. 📝 Automation: Enterprise-grade efficiency. 🤖 Agents: Advanced tool integration. ⚡ Stability: Reliable long-context performance.

📖 Documentation: 👉 Chat - API Doc-CometAPI 👉 Anthropic Messages - API Doc-CometAPI

Experience world-class AI capabilities today! 🚀

🌟 2025-11-20

🎉 CometAPI Launches Nano Banana Pro ! 🎉

🔹 gemini-3-pro-image-preview,gemini-3-pro-image Gemini 3 Pro Image (also known as nanobanana pro) is Google’s flagship image generation model designed for high-fidelity professional workflows. This release introduces "Deep-Context" understanding for highly complex prompts, perfects in-image typography generation, offers distinct object editing without manual masking, and significantly enhances photorealism and lighting physics. Follows the Google standard format. See details: CometAPI Chat Documentation https://apidoc.cometapi.com/gemini-generates-image-20873272e0 GUIDE：https://apidoc.cometapi.com/guide-to-calling-gemini-2-5-flash-image-1425263m0

🎉 CometAPI Launches Grok 4.1 Fast Series Models! 🎉

🚀 Available Models:

  • 🔹 grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning

    A cutting-edge multimodal model designed specifically for high-performance tool calling and complex interaction scenarios. It delivers exceptional logical processing capabilities while maintaining ultra-fast response speeds. Supports a maximum context of 2M tokens.

    Flexible Dual Modes:

    • reasoning: Enhanced logical reasoning, ideal for complex problem-solving.
    • non-reasoning: Optimized for extreme speed, ideal for high-concurrency tasks.

Format Support: Chat format

🌟 2025-11-19

🎉 CometAPI Launches Gemini 3 Pro Model! 🎉

🔹 gemini-3-pro-preview,gemini-3-pro-preview-thinking

Google's most intelligent model with SOTA (state-of-the-art) reasoning and multimodal understanding capabilities, featuring powerful agentic and vibe coding abilities. Max context: 2M tokens; Knowledge cutoff: January 1, 2025.

Key Features:

  • Unified Multimodal: Text, image, audio, and video processing with real-time analysis
  • Million-Token Context: Handle massive documents and codebases
  • Advanced Reasoning: Multi-step problem-solving with RL optimization
  • High Performance: Sparse MoE architecture + Google TPU v6

Best For: AI agents, code generation, multimodal understanding

Format Support: Chat format

🌟 2025-11-14

🎉 Major Update! CometAPI Now Supports the Full GPT-5.1 Model Series! 🎉

🚀 Available Models & Usage Guide

GPT-5.1 is OpenAI's latest flagship model, designed for advanced coding and agent tasks.

  • General Specs: 400k context window, 128k max output, with a knowledge cutoff of September 30, 2024.

🔹 gpt-5.1 & gpt-5.1-chat-latest (For Dialogue & General Tasks)

  • Model IDs: gpt-5.1, gpt-5.1-chat-latest
  • Description: OpenAI's flagship models, ideal for building multi-turn conversational applications that demand powerful reasoning and comprehension.
  • Recommended Endpoint: /v1/chat
  • Documentation: 👉 Check out the Chat API documentation

🔹 gpt-5.1-codex (For Professional Code Tasks)

  • Model ID: gpt-5.1-codex
  • Description: Optimized for coding tasks like code generation, completion, and analysis to leverage its best-in-class coding capabilities.
  • Required Endpoint: /v1/responses (Note: This endpoint must be used for this model.)
  • Documentation: 👉 Check out the Responses API documentation

🎉 CometAPI Grand Launch of qwen-image and qwen-image-edit! 🎉

🚀 Available Models:

🔹 qwen-image

🔹 qwen-image-edit

  • qwen-image: It is a universal image generation model, mainly used to generate completely new images based on text, emphasizing the ability to create from scratch. It is suitable for scenarios such as creative generation, stylized drawing, and more.

    It is trained on large-scale vision-language models, supports multi-language prompts, but its core focus is on generation rather than editing.

qwen-image-edit: An optimized version based on Qwen-Image, specifically tailored for image editing tasks. It features stronger capabilities in local modifications and consistency preservation. It can not only generate new images but also perform precise edits on existing images.

🌟 2025-11-12

🎉 CometAPI proudly launches the new gpt-image-1-mini model! 🎉

🚀 Available Models:

🔹 gpt-image-1-mini

  • gpt-image-1-mini: OpenAI's cost-effective image generation model, supporting text/image as input and outputting images; suitable for large-scale, cost-sensitive generation scenarios.

  • The above models follow the OpenAI standard image generation format for calls. For details, refer to: Text-to-Image, Image-to-Image

📢 Additional Announcements:

  • CometAPI Partners with Bria! CometAPI has reached a cooperation with Bria, and in November 2025, bria all interfaces will be freely open to all users for calls. Have a try!

  • Sora Asynchronous Format Update: CometAPI has completed the replacement of Sora's asynchronous format and no longer supports the open chat format.

    • Please use sora-2-pro or sora-2 models, which call this interface (official per-second billing): Sora API.
    • Use sora-2-all or sora-2-pro-all models, which call this interface (billed per item, after discount: sora-2-all: 0.08, sora-2-pro-all: 0.8): Sora All API.

🌟 2025-11-10

🎉 CometAPI Excitingly Launches K2-Thinking Series New Models! 🎉

🚀 Available Models:

🔹 k2-thinking

🔹 k2-thinking-turbo

  • k2-thinking: Moonshot AI's most advanced open reasoning model, extending the K2 series. It is a thinking model with universal Agentic capabilities and reasoning abilities. Supports 256K tokens context window.
  • k2-thinking-turbo: Based on k2-thinking, it provides faster response speeds and higher concurrency capabilities, supporting the same 256K context and reasoning functions, suitable for high-efficiency scenarios.
  • The above models follow the OpenAI Chat standard format for invocation. For details, refer to: https://apidoc.cometapi.com/chat

🌟 2025.11.07

Comet Major Update Announcement: Sora-2 Invocation Method Optimization

To improve efficiency and stability, we will optimize the Sora-2 invocation method starting from UTC 2025-11-11 8:00.

Key Changes

  • No longer supported: Using the OpenAI reverse-engineered Chat format for invocation.
  • New asynchronous format: Model name switches to sora-2-all or sora-2-pro-all to call the asynchronous interface format (notification will be sent as soon as it's live).
  • Pricing remains unchanged.

Recommended Actions

  • Please complete the interface switch by the update time to avoid service interruption.
  • We will provide the new format as soon as possible for testing to ensure a smooth transition.
  • Currently, you can continue using the official format (billed per second). For details, see the documentation: https://apidoc.cometapi.com/create-video-22425640e0.

If you have any questions, please contact customer service. We are committed to providing a better experience—thank you for your support!

🌟 2025.11.03

🎬 KLING New Features

  • 🧑‍💻 Digital Human Tasks: Supports creating digital human tasks (first perform speech synthesis to obtain taskid and audioid), generating highly realistic digital human videos to enhance interactivity.
  • 🚀 Advanced Model: Added kling-v2-5-turbo, providing faster speed and higher video quality (Pro mode only).
  • 🛠️ Other Features: Including image recognition, face recognition (lip-sync), task creation (lip-sync), speech synthesis, seamlessly integrated into the video generation workflow.
  • 📚 API Calls: View API Documentation

💥 Sora-2 Pricing Update (CometAPI Official Format)

  • 📉 Price Reduction: Sora-2 model calls via CometAPI are now discounted to 80% of the official price, making high-quality video generation more accessible and cost-effective for all users.
  • 🛠️ Integration Details: Seamlessly integrate Sora-2 into your workflows with standard CometAPI calls. For full API reference, check the updated documentation.
  • 🚀 Availability: This pricing update is live now—start saving on your Sora-2 tasks today!

🔥 All New Features Are Now Fully Available, Welcome to Test and Experience! 🔥

⭐️ 2025-10-17

🎉 CometAPI Model Update Announcement 🎉

We've added three powerful AI models, all supporting chat format calls to accelerate your AI application development!

🚀 New Models

Claude Haiku 4.5

  • Model ID: claude-haiku-4-5-20251001 / cometapi-haiku-4-5-20251001
  • ⚡ Low Latency & High Throughput: Optimized for real-time, high-concurrency scenarios
  • 🧠 Configurable Reasoning Depth: Supports "extended thinking" mode
  • 📄 Massive Context: Up to 200K input tokens, 8K output tokens
  • 💻 Strong Code Capabilities: Code generation, debugging, tool calling
  • 💰 Cost Advantage: ~1/3 the cost of Sonnet 4
  • 🔧 Format Support: Claude native message format + chat format

GLM-4.6

  • Zhipu AI's latest flagship model with 355B total params, 32B active
  • 💻 Coding Excellence: Aligns with Claude Sonnet 4, best in China
  • 📚 Extended Context: Expanded from 128K to 200K tokens
  • 🧠 Enhanced Reasoning: Supports tool calling during inference
  • 🔍 Search Optimization: Improved tool calling and agent performance
  • ✍️ Better Writing: Enhanced style, readability, and role-playing alignment
  • 🌍 Multilingual: Boosted cross-language translation capabilities
  • 🔧 Format Support: Chat format

Veo3.1 & Veo3.1-Pro

  • Google's latest AI video generation models for high-quality video creation
  • 🎬 High Resolution: 1080p video generation
  • 🎵 Synchronized Audio: Dialogue, ambient sounds, effects with native lip-sync
  • ⏱️ Video Length: Generate seamless clips up to 8 seconds
  • 🎨 Creative Control: Reference image support, first/last frame setting, cinematic presets
  • ⚡ Dual Variants: Veo3.1 (standard quality) + Veo3.1-Pro (maximum quality)
  • 🔧 Format Support: Async calls + chat format

All models support chat format calls, with Claude models additionally supporting native message format for maximum integration flexibility!

🌟 2025-10-10

🎉 Major Model Update - 3 New AI Services! 🎉

🔥 GPT-5 Complete Series (7 Models)

World's most advanced reasoning models with 400k context window

  • gpt-5-minimal - Lightning-fast for simple tasks
  • gpt-5-low - Speed-optimized (212 tokens/sec)
  • gpt-5-medium - Balanced performance for general use
  • gpt-5-high - Maximum "deep thinking" mode
  • gpt-5-codex-low/medium/high - Specialized for coding & software engineering
  • ✨ Features: State-of-the-art coding, mathematics, visual perception & complex reasoning

🎬 Sora-2 & Sora-2 Pro

  • Official OpenAI video generation with synced audio
  • Realistic physics & object interactions
  • Professional-grade cinematic quality
  • Same pricing as OpenAI official rates

📋 API Documentation:

🌟 2025-10-06

🎉 CometAPI Now Supports GPT-5 Pro! 🎉

We're excited to announce that GPT-5 Pro - OpenAI's most advanced AI model - is now available on CometAPI!

🚀 Key Features:

  • Enhanced Reasoning: Superior performance on complex tasks
  • Advanced Problem Solving: Unparalleled accuracy and depth
  • Multi-Domain Excellence: Exceptional capabilities across all fields

🛠 Usage

Use the following model names in your API calls:

  • gpt-5-pro-2025-10-06
  • gpt-5-pro

📖 API Documentation:

https://apidoc.cometapi.com/response-18535147e0

Ready to experience the next generation of AI? Start building with GPT-5 Pro today!

🌟 2025-10-01

CometAPI Now Supports Sora 2 API Calls

We're excited to announce that CometAPI now fully supports OpenAI's latest Sora 2 video generation model! Developers can now easily access this groundbreaking AI video generation technology through our unified API interface.

Sora 2 Features:

  • ✨ Highly Realistic Video Generation: Creates physics-accurate, visually stunning video sequences perfect for short-form content
  • 🎵 Synchronized Audio & Video: Supports synchronized audio and dialogue generation for complete video content
  • ⏱️ Temporal Consistency: Ensures objects and scenes remain coherent throughout the video duration
  • 🎬 Multi-Style Support: From cinematic quality to anime styles, meeting diverse creative needs
  • 👤 Real-World Cameo Feature: Inject real people, animals, or objects with accurate likeness reproduction
  • 🎯 Advanced Control: Precise editing controls for re-rendering specific objects or scenes
  • 🛡️ Built-in Safety: Comprehensive safety measures and content moderation

Important Notes:

  • ⚠️ Due to limited official compute capacity during the initial launch, you may experience some instability - we appreciate your patience
  • 📡 For video generation using chat format, please use streaming output

API Integration:

Sora-2 is now live and compatible with OpenAI Chat Completions. Switch the base URL to CometAPI and use the key obtained from the CometAPI console to make calls.

Minimal example (replace Authorization with your CometAPI key):

bash curl --location --request POST 'https://api.cometapi.com/v1/chat/completions'
--header 'Authorization: sk-'
--header 'Content-Type: application/json'
--header 'Accept: /'
--header 'Host: api.cometapi.com'
--header 'Connection: keep-alive'
--data-raw '{ "model": "sora-2", "stream": true, "messages": [ { "role": "user", "content": "Generate a cute kitten sitting on a cloud, cartoon style" } ] }'

👉 Visit https://www.cometapi.com to start experiencing Sora 2's powerful capabilities! For questions, join our Discord community: https://discord.com/invite/HMpuV6FCrG

🌟 2025-09-30

🎉 CometAPI Now Supports Claude Sonnet 4.5, DeepSeek-V3.2-Exp, and Gemini 2.5 Flash New Versions! 🎉

🚀 Claude Sonnet 4.5

  • Available Model Names: claude-sonnet-4-5-20250929-thinking, claude-sonnet-4-5-20250929, claude-sonnet-4-5, cometapi-sonnet-4-5-20250929-thinking, cometapi-sonnet-4-5-20250929, cometapi-sonnet-4-5
  • Claude Sonnet 4.5 has world-leading coding capabilities (SOTA-Level Coding). It achieved an astonishing 77.2% accuracy on the authoritative SWE-bench benchmark, which measures real-world software engineering abilities, making it the world's strongest coding model. This means it has made a qualitative leap in handling complex programming tasks, debugging, and even architectural design.

🚀 DeepSeek-V3.2-Exp Highlights

  • The DeepSeek-V3.2-Exp model is an experimental (Experimental) version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1, and conducts exploratory optimization and verification for the training and inference efficiency of long texts.

🚀 Gemini 2.5 Flash Highlights

  • gemini-2.5-flash-preview-09-2025: A model that excels in cost-effectiveness and provides comprehensive features. 2.5 Flash is best suited for large-scale processing of low-latency, high-data-volume tasks that require thinking, as well as agent application scenarios.
  • gemini-2.5-flash-lite-preview-09-2025: The fastest Flash model, specially optimized for cost-benefit and high throughput.
  • Follows the OpenAI chat standard format, see details: CometAPI Chat Documentation

🌟 2025-09-23

🚀 New and Updated Models：

🔹 grok-4-fast-non-reasoning

  • grok-4-fast-non-reasoning: The non-reasoning variant of xAI's Grok-4 Fast series, with a unified architecture for handling fast responses, suitable for real-time search and simple queries. It possesses extremely powerful technical parameters and ecosystem capabilities: context window supports up to 2,000,000 tokens, cost-efficient (input $0.20/million tokens), leading mainstream models.

🔹 grok-4-fast-reasoning

  • grok-4-fast-reasoning: The reasoning variant of xAI's Grok-4 Fast series, supporting long-chain thinking and tool calls, suitable for complex tasks such as mathematical reasoning and agent workflows. Ranked first in the LMArena search arena (1163 Elo), it possesses extremely powerful technical parameters and ecosystem capabilities: context window supports up to 2,000,000 tokens, leading mainstream models.

🔹 grok-code-fast-1

  • grok-code-fast-1: xAI's fast model specifically designed for agent coding, optimized for tool integration such as grep and file editing, achieving 70.8% performance on SWE-Bench-Verified, suitable for automated code generation and debugging. Currently supports text modality, with vision and other features coming soon. It possesses extremely powerful technical parameters and ecosystem capabilities: context window supports up to 256,000 tokens, leading coding-specific models.
  • Follows the OpenAI chat standard format, see details: CometAPI Chat Documentation

🌟 2025-09-11

🚀 New and Updated Models: minimax-hailuo-02, bytedance-seedream-4-0-250828, VEO3 Updated!

🔹 minimax-hailuo-02

  • Support for minimax-hailuo-02 model, which is MiniMax's latest masterpiece, an AI video generation model aimed at completely transforming the video creation process. It not only inherits the advantages of the previous generation Hailuo 01, but also achieves a qualitative leap in core technology and user experience.
  • Click the link to experience it now: https://apidoc.cometapi.com/minimax-conch-generation-14660582e0

🔹 bytedance-seedream-4-0-250828

  • Support for bytedance-seedream-4-0-250828, as a new-generation image creation model, Seedream 4.0 integrates image generation and image editing capabilities into a unified architecture. This enables it to flexibly handle complex multimodal tasks, including knowledge-based generation, complex reasoning, and reference consistency. Compared to its predecessor, it has faster inference speed and can produce stunning high-definition images up to 4K resolution.
  • Click the link to experience it now: https://apidoc.cometapi.com/bytedance-image-generation-19773064e0

🔹 VEO3

  • The entire VEO3 series follows the official price reduction, with comet prices reduced to half of the original, welcome to call.
  • VEO3 now supports asynchronous interfaces for task processing, optimizing the calling efficiency of long-duration tasks and enhancing the overall experience.
  • Click the link to experience it now: https://apidoc.cometapi.com/submit-video-generation-task-18941528e0

🌟 2025-09-07

🎉 CometAPI Heavyweight Launch: kimi-k2-250905 and qwen3-max-preview! 🎉

🔹 kimi-k2-250905

  • kimi-k2-250905: Moonshot AI's Kimi K2 series 0905 version, supporting ultra-long context (up to 256k tokens, frontend and tool calling).
  • 🧠 Enhanced Tool Calling: 100% accuracy, seamless integration, suitable for complex tasks and integration optimization.
  • ⚡️ More Efficient Performance: TPS up to 60-100 (standard API), up to 600-100 in Turbo mode, providing faster responses and improved reasoning capabilities, with knowledge cutoff to mid-2025.

🔹 qwen3-max-preview

  • qwen3-max-preview: Alibaba's Tongyi Qianwen team's latest developed Qwen3-Max-Preview model, positioned as the peak performance in the series.
  • 🧠 Powerful Multimodal and Reasoning: Supports ultra-long context (up to 128k tokens) and multimodal input, excels in complex reasoning, code generation, translation, and creative content.
  • ⚡️ Breakthrough Improvements: Significant optimization in multiple technical indicators, faster response speed, knowledge cutoff to 2025, suitable for enterprise-level high-precision AI applications.

✅ All models belong to the default group, with seamless integration. It is recommended to choose the most suitable version based on your specific business scenarios (performance, speed, cost) to maximize application value.

🌟 2025-08-27

🔹 gemini-2.5-flash-image-preview, gemini-2.5-flash-image

  • gemini-2.5-flash-image-preview, gemini-2.5-flash-image: Gemini 2.5 Flash Image (also known as nano-banana) is Google’s most advanced image generation and editing model. This update enables you to blend multiple images into a single image, maintain character consistency to tell richer stories, perform targeted transformations using natural language, and use Gemini’s world knowledge to generate and edit images.
  • Please click: https://apidoc.cometapi.com/gemini-generates-image-20873272e0

🌟 2025-08-22

🔹 deepseek-v3.1, deepseek-v3-1-250821

  • deepseek-v3.1, deepseek-v3-1-250821: DeepSeek-V3.1 is DeepSeek's all-new hybrid inference model.
  • 🧠 Hybrid inference: Think & Non-Think — one model, two modes
  • ⚡️ Faster thinking: DeepSeek-V3.1 reaches answers in less time vs. DeepSeek-R1-0528
  • Follows the OpenAI chat standard format, see details: CometAPI Chat Documentation

🔹 Kling

  • ✨ Massive Video Effects Library Expansion: Added 63 new video effects (62 single-subject effects and 1 two-person interactive effect), bringing the total to 80 available effects for more creative choices.
  • 🔊 Video-to-Audio Optimization: The video-to-audio generation feature now supports full-resolution video uploads for more precise sound effect matching.
  • 📈 Multi-Image to Video Performance Skyrockets: Experience a 102% improvement over the previous version! See significant enhancements in subject consistency, dynamic quality, and interaction naturalness. This is a seamless upgrade with no code changes required.
  • 🎬 Text-to-Video Quality Upgrade: Version 1.6 now supports the generation of higher-quality videos.
    • Parameter Example: "mode": "pro"
  • Documentation: Kling Video Generation
  • 🎨 Image Generation Model Update: The new kling-v2-new model is now live, supporting nearly 300 image styles to maximize your creativity!
  • Documentation: Kling Image Generation

🌟 2025-08-18

🚀 New and Updated Models: Runway, VEO3, Hunyuan3D, Midjourney Fully Updated!

🔹 Runway

  • Runway model adds multiple core functions, expanding video and image generation capabilities:
  • Video to Video: Video to video generation.
  • Text to Image: Text to image generation.
  • Video Upscale: Video super-resolution enhancement.
  • Control a Character: Character control function.
  • Click the link to experience it now: https://apidoc.cometapi.com/generate-a-video-from-a-video-20308134e0

🔹 VEO3

🔹 Hunyuan3D

🌟 2025-08-08

🔹 GPT-5 Series

  • gpt-5, gpt-5-2025-08-07: OpenAI's flagship model, widely recognized as the industry's most powerful for coding, reasoning, and agentic tasks. It is designed to handle the most complex cross-domain challenges and excels in code generation, advanced reasoning, and autonomous agents, making it the premier choice for users demanding peak performance.
  • gpt-5-chat-latest: The continuously updated version of GPT-5. It always incorporates the latest features and optimizations, recommended for applications that need to stay current with the latest model capabilities.

🔹 GPT-5 Mini Series

  • gpt-5-mini, gpt-5-mini-2025-08-07: The cost-effective version of GPT-5, specifically optimized for speed and cost. It strikes an excellent balance between performance and affordability, making it the ideal choice for everyday tasks like general chat, content creation, and routine Q&A.

🔹 GPT-5 Nano Series

  • gpt-5-nano, gpt-5-nano-2025-08-07: The fastest and most cost-effective lightweight version in the GPT-5 family. It is perfect for scenarios requiring high throughput and instant responses, such as text classification, sentiment analysis, summary extraction, and data formatting.

API Call Instructions:

  • gpt-5-chat-latest should be called using the standard /v1/chat/completions format.
  • For other models (gpt-5, gpt-5-mini, gpt-5-nano, and their dated versions), using the /v1/responses format is recommended.
  • For details, please refer to: https://apidoc.cometapi.com/api-13851472

Note

  • Important: top_p is not supported by this series of models.
  • Temperature Settings
    • gpt-5-chat-latest: Supports custom temperature values between 0 and 1 (inclusive).
    • All other GPT-5 models: The temperature is fixed at 1. You may set it to 1 or omit it (defaults to 1).
  • When calling the GPT-5 series models (excluding gpt-5-chat-latest), the max_tokens field should be changed to max_completion_tokens.

🌟 2025-08-06

🔹 claude-opus-4-1-20250805

  • claude-opus-4-1-20250805: Anthropic's flagship Claude Opus 4.1 model, achieving major breakthroughs in programming, reasoning, and agentic tasks, with SWE-bench Verified reaching 74.5%.
  • Significantly enhanced multi-file code refactoring, debugging precision, and detail-oriented reasoning capabilities. This model is suitable for demanding programming and reasoning scenarios.
  • We have also added cometapi-opus-4-1-20250805 specifically for Cursor integration.

🔹 claude-opus-4-1-20250805-thinking

  • claude-opus-4-1-20250805-thinking: Claude Opus 4.1 version with extended thinking capabilities, providing up to 64K tokens of deep reasoning capacity.
  • Optimized for research, data analysis, and tool-assisted reasoning tasks, with powerful detail-oriented reasoning abilities.
  • We have also added cometapi-opus-4-1-20250805-thinking specifically for Cursor integration.

🔹 gpt-oss-120b

  • gpt-oss-120b: OpenAI's released 117B parameter Mixture of Experts (MoE) open-source model, designed for high-level reasoning, agentic, and general production use cases.

🔹 gpt-oss-20b

  • gpt-oss-20b: 21B parameter open-source MoE model with 3.6B active parameter architecture, optimized for low-latency inference and consumer-grade hardware deployment.
  • All above models follow the OpenAI chat standard format for API calls. For details, please refer to: https://apidoc.cometapi.com/api-13851472

🌟 2025-08-05

🚀 Feature Updates: gemini-2.5-flash-lite, o3 & o4-mini Deep Research, Volcano Engine Generation Models

- gemini-2.5-flash-lite - Google's most cost-effective model, built for large-scale tasks!

  • ⚡️ High Efficiency: Designed for large-scale, low-latency applications.
  • 🔧 Standard Format: Follows the OpenAI chat standard format, see details: CometAPI Chat Documentation

- o3 & o4-mini Deep Research Agents - Get in-depth analysis reports with web-connected research agents!

  • 🧠 Advanced Analysis: Supports multi-step reasoning and provides reports with citations.
  • 🤖 Available Models: o3-deep-research, o3-deep-research-2025-06-26, o4-mini-deep-research, o4-mini-deep-research-2025-06-26
  • 📚 How to Call: The four deep research models above must be called using the following format:

curl --location 'https://api.cometapi.com/v1/responses'
--header 'Authorization: Bearer sk-xxxxx'
--header 'Content-Type: application/json'
--data '{ "model": "o3-deep-research-2025-06-26", "stream": true, "reasoning": { "summary": "detailed" }, "tools": [ { "type": "web_search_preview" } ], "input": "who are you" }'

- Volcano Engine Video & Image Models - Experience powerful new video and image models!

  • 🎬 Video Generation: Create videos from images (bytedance-seedance-1-0-pro, bytedance-seedance-1-0-lite-i2v-250428) or text (bytedance-seedance-1-0-lite-t2v-250428).
  • 🎨 Image Generation & Editing: Generate images with bytedance-seedream-3.0-t2i or edit them using prompts with bytedance-seedEdit-3.0-i2i.

🌟 2025-07-31

🚀 Feature Updates: MJ Video Generation, Flux-Kontext Multi-Image Reference, Kling-v1-6 Multi-Image Reference

- MJ Video Generation - Transform static images into dynamic video effects!

  • 🎬 New: /mj/submit/imagine endpoint now supports video generation
  • 🎨 Use cases: Animated effects, creative video generation
  • 📚 View Documentation

- Flux-Kontext Multi-Image Reference - Enhanced AI creation!

  • 🖼️ Update: Now supports up to 4 reference images (previously 1)
  • 🔧 Models: flux-kontext-max and flux-kontext-pro only
  • 📚 View Documentation

- Kling-v1-6 Multi-Image Reference - Better video quality!

  • 📸 Feature: Up to 4 reference images for improved generation
  • 🎯 Model: kling-v1-6 only
  • 📚 View Documentation

🌟 2025-07-11

🚀 CometAPI supports Claude Code!

Add power to your development workflow. We're excited to announce that CometAPI now fully supports the powerful Claude Code.

What does this mean for you?

  • Top Artificial Intelligence features: Easily generate, debug and optimize code using models built specifically for developers.
  • ⚙️ Flexible Model Selection: Our comprehensive range of models allows you to develop more seamlessly.
  • Seamless Integration: APIs are always available. Integrate Claude Code directly into your existing workflow in minutes.

Ready to build faster? Please click on the link below to make a call.