Best LLM Routers in China

OpenRouter serves as a consolidated interface for various large language models (LLMs). It efficiently identifies the most competitive prices and optimal latencies/throughputs from numerous providers, allowing users to establish their own priorities for these factors. There’s no need to modify your existing code when switching between different models or providers, making the process seamless. Users also have the option to select and finance their own models. Instead of relying solely on flawed evaluations, OpenRouter enables the comparison of models based on their actual usage across various applications. You can engage with multiple models simultaneously in a chatroom setting. The payment for model usage can be managed by users, developers, or a combination of both, and the availability of models may fluctuate. Additionally, you can access information about models, pricing, and limitations through an API. OpenRouter intelligently directs requests to the most suitable providers for your chosen model, in line with your specified preferences. By default, it distributes requests evenly among the leading providers to ensure maximum uptime; however, you have the flexibility to tailor this process by adjusting the provider object within the request body. Prioritizing providers that have maintained a stable performance without significant outages in the past 10 seconds is also a key feature. Ultimately, OpenRouter simplifies the process of working with multiple LLMs, making it a valuable tool for developers and users alike.

Anyscale is a configurable AI platform that unifies tools and infrastructure to accelerate the development, deployment, and scaling of AI and Python applications using Ray. At its core is RayTurbo, an enhanced version of the open-source Ray framework, optimized for faster, more reliable, and cost-effective AI workloads, including large language model inference. The platform integrates smoothly with popular developer environments like VSCode and Jupyter notebooks, allowing seamless code editing, job monitoring, and dependency management. Users can choose from flexible deployment models, including hosted cloud services, on-premises machine pools, or existing Kubernetes clusters, maintaining full control over their infrastructure. Anyscale supports production-grade batch workloads and HTTP services with features such as job queues, automatic retries, Grafana observability dashboards, and high availability. It also emphasizes robust security with user access controls, private data environments, audit logs, and compliance certifications like SOC 2 Type II. Leading companies report faster time-to-market and significant cost savings with Anyscale’s optimized scaling and management capabilities. The platform offers expert support from the original Ray creators, making it a trusted choice for organizations building complex AI systems.

TrueFoundry is an Enterprise Platform as a service that enables companies to build, ship and govern Agentic AI applications securely, at scale and with reliability through its AI Gateway and Agentic Deployment platform. Its AI Gateway encompasses a combination of - LLM Gateway, MCP Gateway and Agent Gateway - enabling enterprises to manage, observe, and govern access to all components of a Gen AI Application from a single control plane while ensuring proper FinOps controls. Its Agentic Deployment platform enables organizations to deploy models on GPUs using best practices, run and scale AI agents, and host MCP servers - all within the same Kubernetes-native platform. It supports on-premise, multi-cloud or Hybrid installation for both the AI Gateway and deployment environments, offers data residency and ensures enterprise-grade compliance with SOC 2, HIPAA, EU AI Act and ITAR standards. Leading Fortune 1000 companies like Resmed, Siemens Healthineers, Automation Anywhere, Zscaler, Nvidia and others trust TrueFoundry to accelerate innovation and deliver AI at scale, with 10Bn + requests per month processed via its AI Gateway and more than 1000+ clusters managed by its Agentic deployment platform. TrueFoundry’s vision is to become the Central control plane for running Agentic AI at scale within enterprises and empowering it with intelligence so that the multi-agent systems become a self-sustaining ecosystem driving unparalleled speed and innovation for businesses. To learn more about TrueFoundry, visit truefoundry.com.

Introducing the ultimate developer platform for AI characters, which offers a comprehensive solution that surpasses traditional large language models (LLMs) by incorporating configurable safety features, knowledge bases, memory capabilities, narrative management, and multimodal functionality. Create characters with unique personalities and situational awareness that adhere to specific themes or branding guidelines. Designed for effortless integration into real-time applications, the platform is optimized for both scalability and performance, ensuring smooth operation. Inworld specializes in providing low-latency interactions that adapt to the demands of your application, while orchestrating across multiple LLMs to enhance the quality of interactions while reducing both inference time and costs. Each interaction is contextually aware, ensuring that models are responsive to their environment. You can implement custom knowledge, safety measures, and narrative management tools to maintain the integrity of your AI's character, whether it is in-world or aligned with brand identity. By prioritizing personality in AI design, our multimodal system captures the breadth of human expression, making interactions more engaging and authentic. This innovative approach not only elevates the user experience but also redefines the potential of AI character development.

Unlock the potential of selecting the ideal LLM tailored to your specific requirements while enhancing quality, speed, and cost-effectiveness. With a single API key, you can seamlessly access every LLM from various providers through a standardized interface. You have the flexibility to set your own parameters for cost, latency, and output speed, along with the ability to establish a personalized quality metric. Customize your router to align with your individual needs, allowing for systematic query distribution to the quickest provider based on the latest benchmark data, which is refreshed every 10 minutes to ensure accuracy. Begin your journey with Unify by following our comprehensive walkthrough that introduces you to the functionalities currently at your disposal as well as our future plans. By simply creating a Unify account, you can effortlessly connect to all models from our supported providers using one API key. Our router intelligently balances output quality, speed, and cost according to your preferences, while employing a neural scoring function to anticipate the effectiveness of each model in addressing your specific prompts. This meticulous approach ensures that you receive the best possible outcomes tailored to your unique needs and expectations.

Utilize the most advanced AI model router to ensure you engage the optimal model at the perfect moment. Maximize the effectiveness of each model with unmatched speed and accuracy. Not only does Not Diamond function seamlessly right away, but you can also create a personalized router using your own evaluation data, thus tailoring model routing specifically to your needs. Choose the appropriate model faster than it takes to process a single token, allowing you to make use of more efficient and cost-effective models without compromising on quality. Craft the ideal prompt for each language model (LLM) so that you consistently access the right model with the appropriate prompt, eliminating the need for manual adjustments and trial-and-error. Importantly, Not Diamond operates as a direct client-side tool rather than a proxy, ensuring all requests are securely handled. You can activate fuzzy hashing through our API or deploy it directly within your infrastructure to enhance security. For any given input, Not Diamond instinctively identifies the most suitable model to generate a response, achieving remarkable performance that surpasses all leading foundation models across key benchmarks. Moreover, this capability not only streamlines workflows but also enhances overall productivity in AI-driven tasks.

Vercel AI Gateway is a centralized AI model routing and infrastructure platform designed to help developers build, deploy, and scale AI-powered applications using a single unified interface for multiple AI providers and models. The platform enables developers to access text, image, and video generation models from leading AI labs including OpenAI, Anthropic, xAI, and other providers through one API endpoint, one authentication layer, and one management dashboard. AI Gateway simplifies AI application development by consolidating model routing, usage monitoring, billing, failover management, and observability into a single system, eliminating the need to integrate separately with multiple AI vendors. Developers can use the Vercel AI SDK or OpenAI-compatible APIs to build AI applications with support for streaming responses, stateful agents, multimodal generation, tool calling, and conversational workflows. The platform includes built-in resiliency features such as automatic provider failovers and workload routing to maintain uptime during outages or degraded model performance. AI Gateway also provides unified cost tracking and transparent billing with no markup over provider pricing, helping teams monitor AI usage across applications and providers more effectively. In addition to text generation, the platform supports image generation and editing workflows, as well as production-ready AI video generation capabilities accessible through prompt-based interfaces. Integrated developer tooling, SDKs for multiple programming languages, authentication management, and deployment workflows make Vercel AI Gateway particularly suited for modern web applications, AI agents, SaaS platforms, and developer-focused AI products.

LiteLLM serves as a comprehensive platform that simplifies engagement with more than 100 Large Language Models (LLMs) via a single, cohesive interface. It includes both a Proxy Server (LLM Gateway) and a Python SDK, which allow developers to effectively incorporate a variety of LLMs into their applications without hassle. The Proxy Server provides a centralized approach to management, enabling load balancing, monitoring costs across different projects, and ensuring that input/output formats align with OpenAI standards. Supporting a wide range of providers, this system enhances operational oversight by creating distinct call IDs for each request, which is essential for accurate tracking and logging within various systems. Additionally, developers can utilize pre-configured callbacks to log information with different tools, further enhancing functionality. For enterprise clients, LiteLLM presents a suite of sophisticated features, including Single Sign-On (SSO), comprehensive user management, and dedicated support channels such as Discord and Slack, ensuring that businesses have the resources they need to thrive. This holistic approach not only improves efficiency but also fosters a collaborative environment where innovation can flourish.

Pruna leverages generative AI technology to help businesses generate high-quality visual content swiftly and cost-effectively. It removes the conventional requirements for studios and manual editing processes, allowing brands to effortlessly create tailored and uniform images for advertising, product showcases, and online campaigns. This innovation significantly streamlines the content creation process, enhancing efficiency and creativity for various marketing needs.

LangDB provides a collaborative, open-access database dedicated to various natural language processing tasks and datasets across multiple languages. This platform acts as a primary hub for monitoring benchmarks, distributing tools, and fostering the advancement of multilingual AI models, prioritizing transparency and inclusivity in linguistic representation. Its community-oriented approach encourages contributions from users worldwide, enhancing the richness of the available resources.

LLM Gateway is a completely open-source, unified API gateway designed to efficiently route, manage, and analyze requests directed to various large language model providers such as OpenAI, Anthropic, and Gemini Enterprise Agent Platform, all through a single, OpenAI-compatible endpoint. It supports multiple providers, facilitating effortless migration and integration, while its dynamic model orchestration directs each request to the most suitable engine, providing a streamlined experience. Additionally, it includes robust usage analytics that allow users to monitor requests, token usage, response times, and costs in real-time, ensuring transparency and control. The platform features built-in performance monitoring tools that facilitate the comparison of models based on accuracy and cost-effectiveness, while secure key management consolidates API credentials under a role-based access framework. Users have the flexibility to deploy LLM Gateway on their own infrastructure under the MIT license or utilize the hosted service as a progressive web app, with easy integration that requires only a change to the API base URL, ensuring that existing code in any programming language or framework, such as cURL, Python, TypeScript, or Go, remains functional without any alterations. Overall, LLM Gateway empowers developers with a versatile and efficient tool for leveraging various AI models while maintaining control over their usage and expenses.

TensorBlock is an innovative open-source AI infrastructure platform aimed at making large language models accessible to everyone through two interrelated components. Its primary product, Forge, serves as a self-hosted API gateway that prioritizes privacy while consolidating connections to various LLM providers into a single endpoint compatible with OpenAI, incorporating features like encrypted key management, adaptive model routing, usage analytics, and cost-efficient orchestration. In tandem with Forge, TensorBlock Studio provides a streamlined, developer-friendly workspace for interacting with multiple LLMs, offering a plugin-based user interface, customizable prompt workflows, real-time chat history, and integrated natural language APIs that facilitate prompt engineering and model evaluations. Designed with a modular and scalable framework, TensorBlock is driven by ideals of transparency, interoperability, and equity, empowering organizations to explore, deploy, and oversee AI agents while maintaining comprehensive control and reducing infrastructure burdens. This dual approach ensures that users can effectively leverage AI capabilities without being hindered by technical complexities or excessive costs.

OrcaRouter serves as a routing system for AI models that are compatible with OpenAI, efficiently directing prompts to the appropriate models from a wide array, including OpenAI, Anthropic, Gemini, DeepSeek, Qwen, Kimi, and over 200 other leading and open-source models. Its design aims to maintain the high quality of responses while minimizing costs associated with AI inference by evaluating each prompt and directing complex reasoning tasks to premium models while assigning simpler tasks to more economical open-source options. The routing process is meticulously quality-graded, avoiding arbitrary swaps for cheaper models, and every request clearly indicates the difficulty rating, chosen model, provider, and associated costs, ensuring that routes remain transparent, accountable, and reproducible. Developers can easily switch models by updating the API base URL, while previously established SDKs, model names, and streaming functionalities remain operational. Additionally, OrcaRouter features seamless automatic failover capabilities, allowing for traffic rerouting without interruption should a provider experience downtime, thus preventing disruptions for users. It also offers comprehensive API key management that incorporates spending limits, model allowlists, rate restrictions, and budget compliance, among other functionalities, ensuring robust control over resource usage. This combination of features makes OrcaRouter an indispensable tool for optimizing AI model utilization in various applications.

Factory Router is an automated model-selection system tailored for autonomous software engineering workflows, aiming to achieve top-tier performance while minimizing costs and enhancing reliability. Rather than relying on engineers to manually identify the optimal model for each task, Factory Router intelligently selects the appropriate model for each Droid session from a varied collection of advanced and efficient models. Routine tasks such as answering simple queries, executing mechanical refactors, making documentation updates, addressing minor bugs, and conducting search-intensive investigations can be efficiently managed by the more streamlined models, whereas complex assignments that require in-depth reasoning can be assigned to the cutting-edge models. Should the chosen model encounter difficulties in completing a task, Factory Router has the capability to transition the session to a more proficient model, ensuring a consistent standard of quality in outcomes. Additionally, it adeptly navigates across different models, providers, and resource capacities whenever issues arise, such as endpoint degradation, rate limits being reached, or limited capacity, thus ensuring uninterrupted operation of Droid sessions. This innovative approach not only enhances productivity but also significantly reduces the burden on engineers, allowing them to focus on more strategic initiatives.

LMOps is a stack that allows you to launch production-ready applications for monitoring, model management and more. Portkey is a replacement for OpenAI or any other provider APIs. Portkey allows you to manage engines, parameters and versions. Switch, upgrade, and test models with confidence. View aggregate metrics for your app and users to optimize usage and API costs Protect your user data from malicious attacks and accidental exposure. Receive proactive alerts if things go wrong. Test your models in real-world conditions and deploy the best performers. We have been building apps on top of LLM's APIs for over 2 1/2 years. While building a PoC only took a weekend, bringing it to production and managing it was a hassle! We built Portkey to help you successfully deploy large language models APIs into your applications. We're happy to help you, regardless of whether or not you try Portkey!

Manifest is a Backend-as-a-Service (BaaS) that streamlines app development by simplifying backend processes. Prioritizing developer efficiency, it enables teams to create a comprehensive backend contained within a single YAML file, which accelerates the journey from concept to deployment. Its seamless integration with any front-end technology allows for effortless scaling as projects grow. Designed for versatility, Manifest accommodates a variety of use cases, ranging from minimum viable products (MVPs) to fully operational applications. This empowers developers to concentrate on their projects, while Manifest manages the complexities of backend infrastructure. As a result, teams can innovate more quickly and efficiently than ever before.

Substrate serves as the foundation for agentic AI, featuring sophisticated abstractions and high-performance elements, including optimized models, a vector database, a code interpreter, and a model router. It stands out as the sole compute engine crafted specifically to handle complex multi-step AI tasks. By merely describing your task and linking components, Substrate can execute it at remarkable speed. Your workload is assessed as a directed acyclic graph, which is then optimized; for instance, it consolidates nodes that are suitable for batch processing. The Substrate inference engine efficiently organizes your workflow graph, employing enhanced parallelism to simplify the process of integrating various inference APIs. Forget about asynchronous programming—just connect the nodes and allow Substrate to handle the parallelization of your workload seamlessly. Our robust infrastructure ensures that your entire workload operates within the same cluster, often utilizing a single machine, thereby eliminating delays caused by unnecessary data transfers and cross-region HTTP requests. This streamlined approach not only enhances efficiency but also significantly accelerates task execution times.

Created by LM-SYS, RouteLLM is a publicly available toolkit that enables users to direct tasks among various large language models to enhance resource management and efficiency. It features strategy-driven routing, which assists developers in optimizing speed, precision, and expenses by dynamically choosing the most suitable model for each specific input. This innovative approach not only streamlines workflows but also enhances the overall performance of language model applications.

FastRouter serves as a comprehensive API gateway designed to facilitate AI applications in accessing a variety of large language, image, and audio models (such as GPT-5, Claude 4 Opus, Gemini 2.5 Pro, and Grok 4) through a streamlined OpenAI-compatible endpoint. Its automatic routing capabilities intelligently select the best model for each request by considering important factors like cost, latency, and output quality, ensuring optimal performance. Additionally, FastRouter is built to handle extensive workloads without any imposed query per second limits, guaranteeing high availability through immediate failover options among different model providers. The platform also incorporates robust cost management and governance functionalities, allowing users to establish budgets, enforce rate limits, and designate model permissions for each API key or project. Real-time analytics are provided, offering insights into token utilization, request frequencies, and spending patterns. Furthermore, the integration process is remarkably straightforward; users simply need to replace their OpenAI base URL with FastRouter’s endpoint while configuring their preferences in the user-friendly dashboard, allowing the routing, optimization, and failover processes to operate seamlessly in the background. This ease of use, combined with powerful features, makes FastRouter an indispensable tool for developers seeking to maximize the efficiency of their AI applications.

Utilizing the top-performing model for each specific request allows us to surpass the capabilities of any individual model. Martian consistently exceeds the performance of GPT-4 as demonstrated in OpenAI's evaluations (open/evals). We transform complex, opaque systems into clear and understandable representations. Our router represents the pioneering tool developed from our model mapping technique. Additionally, we are exploring a variety of applications for model mapping, such as converting intricate transformer matrices into programs that are easily comprehensible for humans. In instances where a company faces outages or experiences periods of high latency, our system can seamlessly reroute to alternative providers, ensuring that customers remain unaffected. You can assess your potential savings by utilizing the Martian Model Router through our interactive cost calculator, where you can enter your user count, tokens utilized per session, and monthly session frequency, alongside your desired cost versus quality preference. This innovative approach not only enhances reliability but also provides a clearer understanding of operational efficiencies.

Requesty is an innovative platform tailored to enhance AI workloads by smartly directing requests to the best-suited model for each specific task. It boasts sophisticated capabilities like automatic fallback systems and queuing processes, guaranteeing seamless service continuity even when certain models are temporarily unavailable. Supporting an extensive array of models, including GPT-4, Claude 3.5, and DeepSeek, Requesty also provides AI application observability, enabling users to monitor model performance and fine-tune their application usage effectively. By lowering API expenses and boosting operational efficiency, Requesty equips developers with the tools to create more intelligent and dependable AI solutions. This platform not only optimizes performance but also fosters innovation in AI development, paving the way for groundbreaking applications.

Sudo provides a comprehensive "one API for all models" solution, allowing developers to seamlessly connect various large language models and generative AI tools—covering text, image, and audio—through a single endpoint. The platform efficiently manages the routing between distinct models to enhance performance based on factors such as latency, throughput, and cost, adapting to your chosen metrics. Additionally, it offers versatile billing and monetization strategies, including subscription tiers, usage-based metered billing, or a combination of both. A unique feature includes the ability to integrate in-context AI-native advertisements, enabling the insertion of context-aware ads into AI-generated outputs while maintaining control over their relevance and frequency. The onboarding process is streamlined; users simply generate an API key, install the SDK in either Python or TypeScript, and begin interacting with the AI endpoints immediately. Sudo places a strong emphasis on minimizing latency—claiming optimization for real-time AI—while also ensuring improved throughput compared to some competitors, all while providing a solution that prevents vendor lock-in. This comprehensive approach allows developers to harness the power of multiple AI tools without being hindered by limitations.

PromptUnit serves as an AI inference intermediary that automatically minimizes AI expenses by acting as a bridge between an application and its AI service providers, requiring no modifications to existing code. Teams simply replace the base URL while maintaining the same SDK, endpoints, response parsing, and error management, allowing PromptUnit to take care of routing, failover, cost monitoring, and quality assessment. It meticulously logs every API interaction, detailing aspects such as model, feature, user segment, token count, latency, and cost, thereby providing immediate insights into AI expenditures before any routing adjustments are implemented. In its observation mode, PromptUnit meticulously monitors traffic, shadow-classifies incoming requests, predicts potential savings, and clarifies routing choices, enabling teams to visualize exact savings prior to activating live routing. After activation, Smart Routing intelligently classifies tasks to direct each request to the most cost-effective model that meets the established quality standards. Additionally, PromptUnit incorporates features like prompt compression, token inflation protection, efficiency scoring for prompts, semantic request caching, and multi-model consensus for enhanced performance. Its comprehensive approach ensures that organizations can optimize their AI usage and manage budgets effectively.

nexos.ai, a powerful model-gateway, delivers AI solutions that are game-changing. Using intelligent decision-making and advanced automation, nexos.ai simplifies operations, boosts productivity, and accelerates business growth.

Bifrost serves as a powerful AI gateway that consolidates access to over 20 providers, including OpenAI, Anthropic, AWS, Bedrock, Google Vertex, Azure, and others, all via a single API. It allows for rapid deployment in mere seconds without the need for any configuration, ensuring features such as automatic failover, load balancing, semantic caching, and robust enterprise governance. In rigorous tests handling 5,000 requests per second, Bifrost introduces a minimal overhead of just 11 microseconds for each request, showcasing its efficiency and reliability for high-demand applications. This makes it an ideal choice for organizations looking to streamline their AI integrations while maintaining performance.