OpenCode Integrations

GPT-5.4 Pro is a high-performance AI model introduced by OpenAI for users who require maximum capability when solving complex problems. It builds on earlier GPT models by integrating advanced reasoning, coding, and workflow automation into a single system. The model is designed to assist professionals with demanding tasks such as data analysis, financial modeling, document generation, and software development. GPT-5.4 Pro can interact directly with computers and applications, allowing AI agents to perform multi-step workflows across different tools and environments. Its extended context window supports up to one million tokens, enabling it to analyze large amounts of information while maintaining accuracy. The model also improves deep web research and long-form reasoning tasks. Developers benefit from improved tool usage and search capabilities that help agents select and operate external tools efficiently. GPT-5.4 Pro delivers stronger coding performance and faster iteration cycles for developers working on complex software projects. It also reduces token usage compared with earlier models, improving cost efficiency and speed. Overall, GPT-5.4 Pro is designed to support advanced professional workflows and AI-powered automation at scale.

GPT-5.4 Thinking is a specialized version of OpenAI’s GPT-5.4 model designed to deliver enhanced reasoning and structured problem-solving in ChatGPT. It integrates improvements in coding, professional knowledge work, and agent-based workflows into a single AI system. One of its key features is the ability to present a plan for its reasoning before generating a final answer. This allows users to review the direction of the response and make adjustments while the model is still working. By enabling this interactive process, GPT-5.4 Thinking helps produce more precise and relevant results. The model is particularly effective for tasks that require deep research or multi-step reasoning. It also maintains context across longer prompts and conversations, reducing confusion in complex discussions. GPT-5.4 Thinking improves how AI interacts with tools and software environments during problem-solving workflows. Its advanced reasoning capabilities allow it to handle analytical tasks with higher consistency and clarity. As a result, GPT-5.4 Thinking is designed to support professionals who need reliable AI assistance for complex work.

GPT-5.4 mini is an advanced AI model designed to provide a balance between high performance, speed, and cost efficiency. It is built to handle a wide range of tasks, including coding, reasoning, tool usage, and multimodal understanding. Compared to earlier versions, GPT-5.4 mini delivers significantly improved performance while operating at faster speeds. The model is particularly effective in environments where low latency is essential, such as real-time coding assistants and interactive applications. It supports capabilities like function calling, tool integration, and image-based reasoning, making it highly versatile. GPT-5.4 mini is also well-suited for subagent architectures, where it can efficiently process smaller tasks within larger AI systems. Developers can use it to automate workflows, analyze data, and build responsive AI-driven applications. Its strong performance across benchmarks shows that it approaches the capabilities of larger models in many scenarios. At the same time, it maintains a lower cost, making it ideal for high-volume usage. Overall, GPT-5.4 mini provides a powerful and scalable solution for modern AI development.

GPT-5.4 nano is a compact and cost-efficient AI model designed for handling lightweight, high-frequency tasks at scale. It is optimized for operations such as classification, data extraction, ranking, and simple coding assistance. The model delivers fast response times, making it suitable for applications where low latency is critical. Compared to earlier nano models, GPT-5.4 nano offers improved performance while maintaining minimal computational cost. It supports key features such as tool usage and structured output generation, allowing it to integrate easily into automated systems. The model is often used as a subagent within larger AI workflows, handling repetitive or supporting tasks efficiently. This approach allows more complex models to focus on higher-level reasoning and decision-making. GPT-5.4 nano is particularly useful in environments that require processing large volumes of requests quickly. Its efficiency makes it ideal for cost-sensitive applications and scalable deployments. Overall, it provides a reliable and fast solution for simple AI-driven tasks.

Xiaomi MiMo-V2.5-Pro is a next-generation open-source AI model designed for advanced reasoning, coding, and long-horizon task execution. It uses a Mixture-of-Experts architecture with over one trillion parameters and a large active parameter set for efficient performance. The model supports an extended context window of up to one million tokens, allowing it to handle complex, multi-step workflows. It is built to perform autonomous tasks, including software development, system design, and engineering optimization. Benchmark results show strong performance across coding, reasoning, and agent-based evaluation tests. MiMo-V2.5-Pro incorporates hybrid attention mechanisms to improve efficiency while maintaining accuracy across long contexts. It is optimized for token efficiency, reducing the computational cost of running complex tasks. The model can integrate with development tools and frameworks to support real-world applications. It is designed to complete tasks that would typically require significant human effort over extended periods. Xiaomi has made the model open source, enabling developers to access and customize it. By combining performance, scalability, and efficiency, MiMo-V2.5-Pro pushes the boundaries of modern AI capabilities.

Xiaomi MiMo-V2.5 is a next-generation open-source AI model that combines agentic intelligence with multimodal capabilities. It is designed to process and understand text, images, and audio within a single architecture. The model uses a sparse Mixture-of-Experts framework with a large parameter count to deliver efficient and scalable performance. It supports a context window of up to one million tokens, allowing it to handle long and complex workflows. MiMo-V2.5 integrates visual and audio encoders to improve perception and cross-modal reasoning. It is capable of performing tasks such as coding, reasoning, and multimodal analysis with strong accuracy. Benchmark results show competitive performance compared to leading AI models in both agentic and multimodal tasks. The model is optimized for token efficiency, balancing performance with lower computational cost. It is designed for real-world applications that require both reasoning and perception. Xiaomi has open-sourced the model, making it accessible for developers and researchers. By combining multimodality, scalability, and efficiency, MiMo-V2.5 pushes forward the development of advanced AI systems.

Puter.js serves as the backend for applications powered by AI, enabling you to leverage your current AI coding tool to develop fully functional apps while reducing AI token usage by as much as 90%. This comprehensive JavaScript library integrates features such as authentication, cloud storage, databases, and support for various AI models including OpenAI, Claude, Gemini, Grok, Kimi, and DeepSeek, all without the need for API keys or complex setup processes. With its streamlined approach, you can focus on creating innovative applications more efficiently.

North Mini Code marks the debut of Cohere’s agentic coding model tailored for developers and serves as the first entry in its next generation of robust models. This compact and efficient open-source solution is specifically crafted for the independent developer community, ensuring remarkable software development capabilities without the need for high-end hardware. Featuring a mixture-of-experts architecture, it comprises a total of 30 billion parameters, with 3 billion of those being active, thereby providing developers with powerful agentic coding functionalities in a streamlined package. The model is finely tuned for various tasks, including code generation, agentic software engineering, and terminal operations, boasting an impressive 256K context length and a maximum generation capacity of 64K. It is designed with real-world developer practices in mind, enabling tasks such as understanding and managing sub-agents, mapping out system architectures, conducting code reviews, and assisting coding agents in navigating intricate software challenges. The integration of these capabilities empowers developers to enhance their productivity and efficiency significantly in software development projects.

Constellation Gate AI serves as an auxiliary defense mechanism for AI agents, positioned strategically between the agent and the model to filter all requests for potential threats and data leaks. This solution functions as an inline gateway for coding agents and model APIs, ensuring protection of workflows while eliminating the need for significant code modifications. Users can direct existing tools such as Claude Code, Cursor, OpenClaw, Codex, or OpenCode to utilize Gate, thereby gaining access to defenses against prompt injection, secret detection, PII redaction, token optimization, and a reliable audit trail. The platform specifically addresses three critical vulnerabilities: prompt injection attacks, leakage of credentials and PII, and unauthorized tool calls. Rather than depending on the model's self-defense mechanisms, Gate preemptively intercepts attacks before they penetrate the model, removes sensitive information prior to the return of responses, and prevents outputs from compromised tools before an agent can act on them. Gate is compatible with the existing calls made by agents, relaying them to the model while meticulously scanning each request and response in both directions, ensuring comprehensive protection against emerging threats. This proactive approach not only enhances security but also instills confidence in users about the integrity and safety of their AI workflows.

HQ serves as a unified AI context platform for teams, enabling all members and AI tools to collaborate from a single workspace where knowledge, skills, and workflows organically grow together, alongside any operating agents. Functioning as an operating system for AI contributors, it integrates seamlessly with Claude Code, Cursor, Codex, ChatGPT, and Claude chat via MCP, allowing every team member and agent to engage with a shared context rather than disjointed chat logs, scattered documents, and isolated processes. By transforming the exemplary efforts of one individual into foundational team infrastructure, HQ allows any prompt or workflow to be converted into a reusable command; subsequently, the /hq-sync feature disseminates it across the entire team, enabling anyone to execute it with ease. As teams progress, knowledge that is typically dispersed across decisions, documentation, playbooks, policies, projects, code, and concepts converges within HQ, establishing a singular source of truth that every agent can access, repurpose, and build upon. Furthermore, agents can be integrated into platforms like email and Slack, functioning with the team's collective expertise and insights while retaining comprehensive context for improved collaboration. This holistic approach not only enhances team productivity but also fosters an environment of continuous learning and adaptation.

Big Pickle is a coding-focused AI model offered through OpenCode Zen, a curated model platform built for developers and AI coding agents. The model supports text input, reasoning, and function calling, making it useful for software engineering workflows that require planning, code understanding, and task execution. Big Pickle is designed for long-context use cases, allowing developers to work with larger prompts, broader project context, and multi-file coding tasks. It can be used through OpenCode Zen’s OpenAI-compatible API, which makes it easier to connect with coding agents, developer tools, and automation environments. Big Pickle is part of a broader OpenCode Zen model catalog that includes multiple coding-oriented and reasoning models. Its free pricing in listed model directories makes it attractive for experimentation, prototyping, and high-volume development workflows. Developers can use Big Pickle for code generation, debugging assistance, project analysis, refactoring support, and agentic task planning. The model is especially relevant for users who want a practical coding assistant that balances reasoning capability, accessibility, and cost efficiency. Big Pickle helps developers build, test, and automate software workflows using a model designed for agent-driven coding environments.

Concentrate AI serves as a centralized gateway for rapidly evolving teams, offering a single API that connects to all major LLM providers while consolidating routing, spending, logging, and controls. This platform empowers teams to securely leverage and manage artificial intelligence through a unified API, ensuring that each request is directed towards the most efficient, cost-effective, and high-performing model for specific tasks or workflows. With access to over 130 models, teams can evaluate speed, quality, and expense, seamlessly directing workloads to the most suitable options without having to integrate multiple provider APIs into their environments. Concentrate recognizes that different applications such as support bots, coding agents, internal tools, chat functions, and batch jobs have varying needs, allowing teams to choose model slugs, restrict authorized providers, prioritize based on real-time latency, and implement fallback strategies to redirect traffic when a provider encounters slowdowns, errors, or limitations. Additionally, it offers a comprehensive view of AI utilization for engineering, finance, security, and leadership teams, featuring detailed logs at the request level that include models used, provider information, duration, token usage, expenditure, error rates, alerts, and data export capabilities, thereby enhancing oversight and decision-making in AI deployment. This level of transparency and control allows organizations to optimize their AI strategies effectively.

Condense.chat is an innovative API designed for compressing input for language models, functioning as a drop-in proxy that effectively reduces the size of prompts, retrieved documents, tool outputs, and recurring agent contexts prior to reaching the main models. By minimizing context while maintaining the integrity of Claude Code, it intercepts an agent's expanding session history and processes it through compression models, enabling long-running coding agents to operate with fewer tokens at the start of each new turn. Acting as an intermediary between applications and upstream LLM providers, Condense meticulously tracks conversations as a content-addressed chain, seamlessly compressing any repeated context along the way. Developers can easily integrate this system by directing their SDK to the Condense provider route, adding a Condense key, and retaining their existing provider key without needing to make any additional changes. Compatibly, it supports routes for both Anthropic and OpenAI, and also offers pass-through functionalities for other provider pathways, including model lists and embeddings, ensuring a versatile integration. This makes it an invaluable tool for optimizing interactions with language models while enhancing overall efficiency in processing and managing session data.

The Laguna XS 2.1 is an enhanced coding model that operates as an open weight agentic system, ideal for long-duration tasks on local machines. Featuring a 33-billion-parameter Mixture-of-Experts framework with 3 billion parameters activated per token, this model maintains the efficient architecture of Laguna XS.2 while significantly advancing performance in multilingual software engineering and terminal-style tasks. It is specifically engineered to assist coding agents in reviewing repositories, reasoning through intricate changes, utilizing various tools, executing commands, and maintaining continuity throughout extended projects. With a generous 256K context window, the model enables agents to effectively manage extensive codebases, lengthy histories, and complex multi-step workflows. Laguna XS 2.1 benefits from support from platforms like vLLM, SGLang, NVIDIA TensorRT-LLM, Hugging Face Transformers, and Ollama, with plans for native integration with llama.cpp in the future. The model is offered in various checkpoint formats, including BF16, FP8, INT4, and NVFP4, granting developers the flexibility to select between high fidelity and configurations optimized for limited VRAM or computational resources. This adaptability makes it an excellent choice for a wide range of development environments and requirements.

Spawn serves as an innovative tool within OpenRouter for effortlessly deploying AI coding agents on your infrastructure using just a single command. You can select your desired agent, pick a cloud provider, and Spawn will take care of provisioning a virtual machine, installing the chosen agent along with its necessary dependencies, authenticating to both OpenRouter and the cloud via a CLI OAuth process, configuring all required endpoints and model routing, and finally initiating an SSH session so you can begin your tasks immediately. Each combination of agent and cloud is encapsulated in a standalone script, thus eliminating the need for Terraform or YAML and ensuring that deployments remain portable. The agents supported include Claude Code, OpenClaw, Codex CLI, OpenCode, Kilo Code, Hermes Agent, Junie, Pi, Cursor CLI, and T3 Code, which simplifies the exploration of various coding-agent workflows or allows for seamless switching between them with a single command. In addition to cloud platforms such as DigitalOcean, Sprite, Hetzner Cloud, AWS Lightsail, GCP Compute Engine, and Daytona, Spawn also accommodates local setups or ephemeral local Docker environments. This versatility ensures that developers can choose the best environment suited to their needs.

Bevel serves as a vendor-neutral, Git-integrated control plane tailored for enterprise AI agents, allowing organizations to define their agents, context, skills, tools, permissions, and identities as owned files within their infrastructure, which can then be accessed by any agent runtime through MCP. The context is organized as typed knowledge nodes, each with documented provenance detailing its source, the last modification, and verification timestamps, and this information is compiled into a navigable graph that can be updated and utilized for creating dashboards. Skills are articulated as straightforward Markdown procedures, enabling process owners to easily read, review changes, and transfer them across different runtimes. Additionally, tool manifests outline the capabilities available, while sensitive information is stored securely in a vault, governed by access rules that dictate which agents can read certain files or invoke specific endpoints. Each agent is assigned a unique identity and credentials, ensuring that all actions can be traced back to their source. This comprehensive framework not only enhances security and organization but also promotes transparency and accountability in AI operations.

The new OpenAI API service tier, GPT-5.6 Sol Ultrafast, operates up to 14 times quicker than the Standard processing version, delivering cutting-edge intelligence to applications and workflows where every fleeting moment is crucial. Utilizing Cerebras technology, it boasts the capability to produce as many as 750 output tokens each second, enabling sophisticated reasoning to function at real-time velocities without the need for a more compact or specialized model. This service is particularly tailored for business environments where rapid responses can significantly enhance the capabilities of AI systems. It has various applications, including incident response, where it can swiftly analyze logs, code changes, traces, and engineering reports during ongoing outages; financial research and security, where it can rapidly evaluate fluctuating market signals and identify suspicious transactions; and customer support, where intricate problems can be resolved seamlessly during live conversations. In the realm of e-commerce, it excels at handling product inquiries, verifying inventory status, and customizing product recommendations to enhance user experience. By implementing this advanced service, organizations can expect improved efficiency and effectiveness in their operations.

Peezy Gateway serves as an AI inference gateway designed to provide developers and coding agents with a singular endpoint for accessing cutting-edge open models, eliminating the need for multiple layers of third-party routing. This service is compatible with OpenAI, allowing users to direct existing OpenAI SDKs, command-line agents, and other compatible tools to a unified base URL instead of having to integrate each model provider independently. P0 is in the process of reconstructing the gateway using its own infrastructure, ensuring that open models are delivered directly from its GPU clusters without intermediaries. The anticipated infrastructure will feature B200 and B300 GPU clusters located in private facilities throughout Singapore and China, aiming to establish a quick and direct connection to every model offered. Additionally, the existing p0ag_ API keys and account credits are intended to seamlessly transition during the infrastructure migration, ensuring that current integrations can continue without starting anew when the gateway is relaunched. This not only streamlines the development process but also enhances accessibility for developers in the AI community.

ClawTab oversees the management of Claude Code, Codex, OpenCode, and shell tasks within persistent tmux sessions. An autonomous daemon efficiently manages schedules, monitors agent statuses, assigns task titles, detects questions, sends notifications, and maintains remote connections, all while the desktop application remains inactive. Users can utilize terminal tools, the tmux plugin, or the macOS desktop application to control agents seamlessly. It is possible to access the same live sessions from an iPhone, iPad, or web browser, allowing for real-time output tracking, question responses, and work initiation on a Mac or connected Linux system. All applications and local tools are freely available and licensed under the MIT license. You can self-host the relay without any cost or opt for the hosted Remote service for a subscription fee of $4.99 per month. Additionally, the flexibility of using multiple devices enhances productivity by ensuring you can always stay connected to your work.

Automater serves as a desktop assistant for developers who utilize various AI coding tools and agents. It efficiently processes recognized transcript files stored locally by these tools, compiles session histories into an easily navigable library, and provides insights into agent performance, outstanding sessions, and usage metrics via a convenient system-tray panel. Available in Automater Lite form for Windows, macOS on Apple silicon, and Linux, it ensures that the local archive is maintained on the user's device, allowing for session resumption wherever the originating tool permits. The free Lite version operates without the need for an account, while the premium PRO edition includes features for managing sessions, controlling agents, and enhanced fleet management capabilities. It aims to assist developers in managing their activities across multiple coding platforms instead of replacing those tools or supplying coding agents directly. This dual approach ensures a comprehensive solution for optimizing coding workflows in a multi-tool environment.

Light Studio serves as a desktop application designed for photographers and creators, enabling them to manage and edit their image collections effectively. The software can directly open Lightroom Classic catalogs or convert them into its proprietary Light catalogs, and it seamlessly integrates Lightroom presets and XMP sidecars. Users have the ability to browse their images by date, folder, or album, conduct photo searches, organize faces, manage keywords, and edit metadata, as well as batch-rename files with ease. The editing capabilities are extensive, including adjustments for exposure, color, curves, grading, detail, optics, and cropping, along with features for HDR and panorama merges. Additionally, users can utilize local masks, denoise, super resolution, and tools for removing, healing, and cloning to refine their images further. It also accommodates compatible video files, allowing them to be stored alongside photos. For advanced retouching, users can send images to Photon Studio and subsequently retrieve them back into the library. The system ensures that libraries, edits, face groups, search indexes, and local AI processing remain on the user's computer, and Light Studio is anticipated to be available for macOS, Windows, and Linux platforms in the near future. This software aims to provide a comprehensive solution for photographers seeking an efficient way to manage their creative workflow.

GPT-5.4 is a next-generation AI model created by OpenAI to assist professionals with advanced knowledge work and software development tasks. It brings together major improvements in reasoning, coding, and automated workflows to deliver more capable and reliable results. The model can analyze large datasets, generate detailed reports, create presentations, and assist with spreadsheet modeling. GPT-5.4 also supports complex coding tasks and can help developers build, test, and debug software more efficiently. One of its key advancements is the ability to use tools and interact with software environments to complete multi-step processes. The model supports very large context windows, allowing it to analyze long documents and maintain context across extended conversations. GPT-5.4 also improves web research capabilities by searching and synthesizing information from multiple sources more effectively. Enhanced accuracy reduces hallucinations and helps produce more reliable responses for professional use. The model is available through ChatGPT, developer APIs, and coding environments such as Codex. By combining reasoning, tool usage, and large-scale context understanding, GPT-5.4 enables users to automate complex workflows and produce high-quality outputs.

Verboo Code functions as a coding agent that offers unlimited tokens for a fixed fee. It features ten distinct models, each typically equipped with a one million token context window, which can be easily switched via commands. Users can access the service through four different entry points under a single subscription: an open-source command-line interface, a desktop application compatible with macOS, Windows, and Linux, a browser extension, and an OpenAI-compatible endpoint that integrates seamlessly with Cursor, VS Code, and JetBrains. Importantly, we do not resell any external APIs; instead, we maintain our own inference layer supported by a proprietary routing system and vLLM/SGLang orchestration. This unique approach is what allows us to offer a straightforward pricing model with no undisclosed limits. Additionally, our commitment to transparency and user accessibility sets us apart in the market.

Claude Fable 5.5 is an anticipated but currently unannounced model in Anthropic's Claude family, and Anthropic has not confirmed that a model with this name will be released. As of September 30, 2026, Claude Fable 5.1 remains the latest officially documented Fable model. Fable represents Anthropic's highest-end model tier for demanding reasoning and long-horizon agentic work, while the newer Opus 5.5 and Sonnet 5.5 occupy lower-cost positions in the Claude lineup. Anthropic's current documentation gives Fable 5.1 a 1-million-token context window and maximum output length of 128,000 tokens. It supports text and image inputs with text output and uses adaptive thinking that remains active throughout model operation. Fable 5.1 defaults to high reasoning effort and is listed as having a June 2026 reliable knowledge cutoff and training-data cutoff. API pricing is $10 per million input tokens and $50 per million output tokens, while prompt-cache reads cost $0.25 per million tokens and Batch API processing receives a 50% input and output discount. Anthropic's official documentation currently provides model identifiers for Fable 5.1 across the Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, and Claude Platform on AWS. No equivalent model identifier, specifications, benchmark results, pricing, availability information, or release schedule has been published for Claude Fable 5.5.

AI Usage Tracker is a macOS application designed for those who keep an eye on the activity of AI coding tools and local models while they work. It features a compact interface that can be positioned at the top, bottom, left, or right edge of the screen, presenting important information such as account limits, reset times, and the activity of various agents. Users are able to track their session and weekly usage statistics, receive notifications about resets, and easily switch back to a tracked session when an agent requires further input. This application supports a range of tools including Claude, Codex, Cursor, Gemini, OpenCode, Kimi, Ollama, and LM Studio, with available metrics differing based on the provider and account specifics. Additionally, for compatible local models, it can provide insights into context utilization and generation speeds, and allows the configuration of separate work and personal profiles for select services. To use this application, users must have macOS 15 or newer, and it is compatible with both Apple silicon and Intel-based Macs. Overall, AI Usage Tracker is an essential tool for anyone looking to optimize their interaction with AI coding technologies.

OpenAI Bel is an unconfirmed artificial intelligence model reportedly associated with OpenAI's research into large-scale foundation models. The name has appeared in unofficial discussions describing a possible new generation of pretrained AI systems. Reports suggest that Bel may represent a successor to an earlier internal training effort referred to as Doug. Some accounts describe the project as a potential foundation for future models related to the Astra family and later GPT generations. Unverified claims place its parameter count above 10 trillion, although OpenAI has not disclosed any supporting architectural information. The model's training methodology, supported modalities, context window, and inference capabilities remain unknown. No official benchmark evaluations have established its performance in reasoning, coding, mathematics, or other AI tasks. OpenAI has not announced public access, API availability, pricing, or a release schedule for a model named Bel. The available information therefore characterizes Bel as a rumored research project rather than an established commercial AI product.