The latest AI news and updates of OpenRouter — Unified API for accessing hundreds of LLMs across providers with intelligent routing and optimization. Covering OpenRouter's latest product updates, launches, and analysis from the past 90 days.
OpenRouter14h agoOpenRouter launched the Subagent server tool, allowing models to delegate focused tasks to smaller, cheaper, faster worker models mid-generation. The orchestrator model invokes the tool with a task description, and the worker executes the task independently. Workers can optionally run as sub-agents with their own tools, such as web search, to ground results in fresh sources.
OpenRouter16h agoOpenRouter launched a Benchmarks explorer on its rankings page that allows users to plot Pareto curves across 10 different benchmarks. The tool visualizes trade-offs between price and performance using Artificial Analysis intelligence indices and Designarena ELO scores for coding, UI, game development, and 3D tasks. This helps developers identify the most cost-effective models for specific use cases.
OpenRouter17h agoOpenRouter launched the Activity explorer, a real-time dashboard for tracking AI spending, token usage, and cache performance across models, users, and agents. The tool includes a Trends tab for identifying usage spikes, an Explore tab for granular analytics across any dimension, and a Guardrails tab to monitor security enforcement. It is available now to everyone.
OpenRouterJun 10OpenRouter published guidance showing how to use its Agent SDK's human-in-the-loop primitives to meet incoming AI regulations including the EU AI Act, Colorado's ADMT law, and NIST AI RMF. The guide documents existing SDK hooks that pause execution, persist state, and log human approvals so deployers can gate sensitive agent actions and produce audit trails required by these frameworks.
OpenRouterJun 10OpenRouter has made Anthropic's Claude Fable 5 model available on its platform. This model is designed for complex, long-running coding and autonomous knowledge work, achieving state-of-the-art performance on various benchmarks. Its availability expands access to a frontier AI model for developers building agentic applications.
OpenRouterJun 9OpenRouter introduced its new Advisor server tool, enabling AI models to consult higher-intelligence models during complex tasks. This capability helps prevent models from getting stuck in "doom loops" and allows developers to optimize costs by using expensive reasoning only when necessary.
OpenRouterJun 7OpenRouter now displays real-time cache hit rates and historical traffic data on its Pricing tab. This update provides transparency into how different model providers compare on effective pricing for LLMs like Anthropic's Claude Opus 4.8, enabling users to optimize costs.
OpenRouterJun 5OpenRouter has integrated Sourceful's Riverflow 2.5 image model, which allows users to define a scoring rubric for guiding image generation and adjust reasoning effort. This provides granular control over output quality and composition, enabling more precise alignment with specific creative or brand requirements.
OpenRouterJun 4OpenRouter's automated routing engines now process 13 billion tokens daily, with the coding-specific Pareto Router hitting 1 billion. The milestone coincides with new granular controls that let users manually balance model performance against token costs. This shift highlights how developers are moving from static model selection to dynamic, algorithmic orchestration to manage AI expenses.
OpenRouterJun 2OpenRouter has integrated Microsoft’s new in-house MAI-Image-2.5, MAI-Transcribe-1.5, and MAI-Voice-2 models into its unified API. These models provide a high-performance stack for image, speech, and voice tasks built entirely without third-party distillation.
OpenRouterJun 2OpenRouter has added DigitalOcean’s AI-Native Cloud as an infrastructure provider for high-performance model hosting. The integration delivers industry-leading output speeds for DeepSeek V3.2, allowing developers to prioritize low-latency responses in agentic workflows.
OpenRouterJun 1OpenRouter introduced a new parameter that lets users manually balance model performance against token costs on a 0–10 scale. The update gives developers granular control over how the Auto Router selects from frontier models based on prompt complexity and budget.
OpenRouterJun 1OpenRouter integrated MiniMax-M3, an open-weight multimodal model featuring a 1-million-token context window and specialized sparse attention. By reducing long-context compute costs by 95%, the model enables persistent agentic workflows across massive codebases and video files.
OpenRouterMay 30OpenRouter launched Guardrails, a suite of security and governance tools for managing budgets, data retention, and prompt injections across its unified API. By moving these controls to the routing layer, developers can enforce enterprise-grade safety and cost policies without rewriting code for individual model providers.
OpenRouterMay 29OpenRouter introduced apply_patch, a server-side tool that enables any LLM to propose file creations, updates, or deletions using a unified diff format. By validating diff syntax server-side, the tool allows developers to build model-agnostic coding agents without writing custom parsing logic for every provider's unique output style.
OpenRouterMay 29OpenRouter released a new comparison interface that visualizes live performance metrics, pricing, and token usage trends across hundreds of LLMs. By moving beyond static benchmarks, the tool helps developers select models based on actual production data like p50 latency and reasoning token volume.
OpenRouterMay 28OpenRouter integrated Anthropic's Claude Opus 4.8, delivering significant gains in agentic coding and reasoning at the same price as the previous version. The update introduces a high-speed Fast Mode that provides 2.5x throughput for only twice the standard cost.
OpenRouterMay 26OpenRouter secured a $113 million Series B led by Alphabet's CapitalG to expand its model routing and optimization platform. The funding follows a 5x surge in weekly token volume, signaling a massive shift toward multi-model production workloads in the enterprise.
OpenRouterMay 21OpenRouter integrated Alibaba's Qwen3.7-Max, a flagship model optimized for autonomous agent loops and multi-hour task execution. The update introduces explicit prompt caching for the Qwen series, allowing developers to maintain massive context windows at a 90 percent discount on subsequent requests.
OpenRouterMay 19OpenRouter integrated Google's Gemini 3.5 Flash, a model that outperforms the previous 3.1 Pro version in coding and tool use at a lower price point. With a 1 million token context window and adjustable thinking levels, it provides a cost-effective alternative for complex autonomous workflows.
OpenRouterMay 19OpenRouter released server-side web search and fetch tools that allow any tool-calling model to autonomously browse the live web. By standardizing the tool schema, developers can swap between providers like OpenAI and Anthropic without rewriting their search implementation or domain filters.
OpenRouterMay 18OpenRouter integrated xAI's multimodal suite, enabling developers to generate photorealistic images, short video clips, and natural speech through a single API. The update allows for complex creative workflows that combine xAI's generative models with existing reasoning and coding tools on the platform.
OpenRouterMay 18OpenRouter released a suite of primitives for its Agent SDK designed to support autonomous tasks that run for hours. These tools handle the complex state management and cost controls required to move AI agents from simple chat interactions to reliable, long-running production workflows.
OpenRouterMay 15OpenRouter overhauled its Bring Your Own Key system to support multiple provider keys with tiered priority and granular usage filters. The update allows developers to stack rate limits and automate failovers between their own credentials and shared platform capacity.
OpenRouterMay 15OpenRouter integrated the Recraft V4.1 suite, introducing six specialized models for high-fidelity photorealism, editable vector graphics, and restraint-first product imagery. The update allows developers to programmatically control brand palettes and background colors while benefiting from improved short-prompt adherence.
OpenRouterMay 13OpenRouter enabled a high-speed inference tier for Anthropic's flagship model, delivering 2.5x faster throughput at a 6x price premium. This update allows developers to trade capital for speed in latency-sensitive agentic workflows without sacrificing reasoning depth.
OpenRouterMay 12OpenRouter integrated Perceptron Mk1, a vision-language model designed for spatial grounding and video understanding with structured outputs like bounding boxes and timestamps. The model introduces a reasoning toggle for complex visual tasks at a significantly lower price point than general-purpose frontier models.
OpenRouterMay 12OpenRouter transitioned its production traffic for Claude models to the newly launched Claude Platform on AWS, confirming consistent performance and uptime. This integration gives developers the full suite of native Anthropic features while keeping existing AWS billing and security infrastructure.
OpenRouterMay 11OpenRouter integrated Ring-2.6-1T, a trillion-parameter reasoning model from AntLingAGI that is free to use through May 15th. The model introduces adjustable thinking effort to balance cognitive depth with token costs, making frontier-level reasoning accessible for production agent workflows.
OpenRouterMay 9OpenRouter released Pareto Code, an experimental router that automatically sends API requests to the most affordable coding model that meets a user-defined quality threshold. By setting a minimum performance score, developers can ensure their applications use the best bang-for-the-buck models without manually tracking the latest benchmark leaders.
OpenRouterMay 8OpenRouter introduced human-in-the-loop controls to its Agent SDK, allowing developers to build agents that pause for review on sensitive actions. The update includes hooks to auto-resolve routine tasks while surfacing high-stakes decisions to a human interface. This standardizes how autonomous agents ask for help without losing conversation state.
OpenRouterMay 8OpenRouter integrated the Recraft V4 suite into its unified API, offering models specifically tuned for art-directed composition and professional design taste. The update allows developers to programmatically control brand colors and text layouts, moving AI image generation from generic stock visuals toward functional branding and marketing assets.
OpenRouterMay 7OpenRouter introduced dedicated text-to-speech and transcription endpoints that integrate with its existing unified API and billing system. By aggregating audio models from providers like Google and OpenAI, the update allows developers to build voice agents with automatic fallbacks and centralized observability.
OpenRouterMay 7OpenRouter integrated Google's Gemini 3.1 Flash Lite into its unified API, offering a 1 million token context window and multimodal processing for $0.25 per million input tokens. The update introduces a service tier parameter that allows developers to trade off latency for lower costs on high-volume agentic tasks.
OpenRouterMay 5OpenRouter analyzed real-world usage data and found that GPT-5.5's actual cost increase ranges from 49% to 92% despite OpenAI doubling per-token prices. While the model generates significantly fewer tokens for long-context tasks, users with shorter prompts face the full weight of the price hike without efficiency gains.
OpenRouterMay 4OpenRouter introduced a one-click toggle that restricts API requests to model providers with official zero data retention policies. By moving privacy enforcement to the workspace level, developers can ensure sensitive data is never stored or used for training without managing individual provider settings.
OpenRouterMay 2OpenRouter introduced a new system of model aliases that automatically route API requests to the most recent version of major LLMs. By using tags like -latest, developers can ensure their applications always use the newest capabilities without manually updating model identifiers in their code.
OpenRouterMay 2OpenRouter introduced a beta response caching feature that stores the output of identical API requests at the edge. By skipping the model provider for repeated calls, developers can eliminate token costs and reduce latency from seconds to milliseconds.
OpenRouterMay 1OpenRouter integrated xAI's new Grok-4.3 reasoning model, which features a 1 million token context window and a significant boost in autonomous task performance. The model achieved a 1500 ELO on the GDPval-AA benchmark for economically valuable tasks, surpassing previous flagship models while launching at a lower price point than its predecessor.
OpenRouterApr 30OpenRouter released Owl Alpha, a high-performance foundation model featuring a 1.05 million token context window and native tool-use capabilities. Currently free to use, the model is architected specifically for long-horizon agentic tasks like automated workflows and multi-file code generation.
OpenRouterApr 30alphaXiv now automatically detects AI model mentions in research papers and generates interactive previews with provider data and use-case rankings. By linking directly to OpenRouter, the update allows developers to move from reading a paper to testing a model in a single click.
OpenRouterApr 30OpenRouter launched a Stripe Projects integration that allows developers to create accounts, generate API keys, and set up billing directly from the command line. By moving infrastructure setup into the CLI, the update enables coding agents to autonomously configure the inference providers they need to function.
OpenRouterApr 29OpenRouter's new Audio Input leaderboard shows Google's Gemini models capturing the top seven spots and over 50% of total audio prompts. While competitors like OpenAI and Mistral appear in the top ten, developers are overwhelmingly choosing Gemini's Flash variants for production audio workloads.
OpenRouterApr 28OpenRouter integrated the first public foundation models from Poolside AI, featuring the flagship Laguna M.1 and the efficient Laguna XS.2. These models are architected specifically for long-horizon software engineering and agentic loops rather than general conversation.
OpenRouterApr 28OpenRouter's study of Opus 4.7 reveals that changes to the model's tokenizer have increased actual costs by 12% to 27% for most users. While short prompts have become more efficient, the shift highlights how token density can drive up expenses even when per-token pricing remains stable.
OpenRouterApr 28OpenRouter integrated NVIDIA's Nemotron 3 Nano Omni, a 30B-A3B model that natively processes text, audio, and video in a single inference loop. By using a hybrid Transformer-Mamba architecture, the model reduces the compute cost of video reasoning by 2.5x, making it a high-efficiency perception layer for autonomous agents.
OpenRouterApr 26OpenRouter released a new agent skill that automates the creation of custom agent harnesses and terminal user interfaces. By providing pre-built multi-model inference and tool-calling logic, the tool allows developers to move from raw API access to functional agentic prototypes without writing boilerplate code.
OpenRouterApr 24OpenRouter integrated OpenAI's GPT-5.5 and GPT-5.5 Pro into its unified API, featuring a 1.05 million token context window. The Pro variant introduces a dedicated reasoning parameter that allows developers to monitor and preserve the model's internal thinking process during complex, multi-step tasks.
OpenRouterApr 24OpenRouter is now hosting Tencent's new Hy3-preview model, offering free access to the 295B-parameter Mixture-of-Experts model. This integration allows developers to test frontier-level reasoning and coding capabilities with a 256K context window at no cost.
OpenRouterApr 24OpenRouter added OpenAI's gpt-5.4-image-2 to its unified API, combining the latest reasoning model with high-fidelity image generation. This update allows developers to build workflows where the model refines its own visual prompts to produce more accurate, instruction-aligned assets.
OpenRouterApr 24Xiaomi released the MiMo-V2.5 series on OpenRouter, featuring a 1 million token context window and native multimodal support for image and video tasks. The models are specifically architected for long-horizon agentic workflows and coding, offering reasoning-enabled thinking tokens to improve task stability. By delivering pro-level performance at roughly half the typical inference cost, these models lower the economic barrier for deploying autonomous agents at scale.
OpenRouterApr 24OpenRouter introduced Workspaces, a new organizational layer that allows users to split their account into isolated environments for different projects or teams. By providing independent API keys, guardrails, and routing defaults per workspace, the update enables developers to manage staging and production environments without shared security risks.
OpenRouterApr 21OpenRouter revealed that the trending Elephant Alpha stealth model is officially Ling-2.6-flash, a 100B-parameter model from AntLingAGI. The model is designed for high-reasoning efficiency and is currently free to use for one week on the platform.
OpenRouterApr 15OpenRouter has launched a unified video generation API that provides access to leading video models through a single integration. This update allows developers to build complex multimodal pipelines where text and image models feed directly into video production.
OpenRouterApr 15OpenRouter introduced a dedicated API for reranker models, starting with the Cohere suite. While standard vector search finds similar text, rerankers score those results for actual relevance to ensure the LLM receives the highest-quality context. This update allows developers to manage both retrieval optimization and model inference through a single provider.
OpenRouterApr 14OpenRouter released Elephant Alpha, a 100B-parameter stealth model optimized for high-reasoning tasks with minimal token consumption. Its 256K context window and high throughput make it a specialized option for complex agentic workflows and large-scale document processing.
OpenRouterApr 1OpenRouter introduced Model Fusion, an experimental tool that runs multiple frontier models in parallel and synthesizes their outputs into a single optimized response. By using a multi-stage judging process to analyze and combine results, the system aims to outperform the standalone capabilities of any individual model.
OpenRouterMar 28OpenRouter has extended the free usage window for Xiaomis flagship MiMo-V2-Pro and MiMo-V2-Omni models through April 2nd. This extension allows developers to continue testing high-parameter models with massive context windows for agentic tasks at no cost.
OpenRouterMar 23OpenRouter's TypeScript SDK now supports typed tool context. Define a contextSchema on your tools and mutate context across agentic turns — changes persist and are Zod-validated. A research agent can accumulate sources across iterations.
OpenRouterMar 20OpenRouter's Auto Exacto is now live by default for all tool-calling API requests, routing to providers with the best reliability signals instead of the lowest price. It cut tool error rates by 15–90% across providers in its first few days.
Frequently asked questions