Latest posts and updates from OpenRouter.https://openrouter.ai/https://openrouter.ai/blog/tutorials/text-to-speech/https://openrouter.ai/blog/tutorials/text-to-speech/Our OpenAI-compatible speech endpoint puts TTS models from Mistral, xAI, Microsoft, and more behind one request shape. Here's the path from API key to a playable MP3 in cURL, Python, JavaScript, and the OpenAI SDK, plus the response checks that keep JSON errors out of your audio files.Fri, 11 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/zero-data-retention/https://openrouter.ai/blog/insights/zero-data-retention/ZDR means an AI provider processes your prompt, returns a response, and doesn't store either one afterward. It's a retention guarantee, not a universal privacy policy. This page explains the boundary, compares ZDR with related controls, and shows how to enforce it at the account, guardrail, or request level.Fri, 11 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/fusion-explainer/https://openrouter.ai/blog/insights/fusion-explainer/Fusion is our compound model. It turns one prompt into a short debate among several models: a panel answers in parallel, a judge maps agreement and disagreement, and the calling model writes the final answer. You trade some speed and tokens for quality. This is what it does, what it costs, and when to use it.Thu, 10 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/presets/https://openrouter.ai/blog/tutorials/presets/A preset is config-as-code for your LLM calls: a named, versioned set of models, system prompts, provider routing, and sampling parameters. Define it once, reference it as @preset/your-slug everywhere, and update every app from the dashboard without a redeploy.Thu, 10 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/nano-banana/https://openrouter.ai/blog/tutorials/nano-banana/Send a source image and an edit prompt in one request, get the edited image back, and change the editing model by editing a single field. Runnable Python and TypeScript included.Wed, 09 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/seedance-2-5-review/https://openrouter.ai/blog/insights/seedance-2-5-review/Seedance 2.5 trades resolution for length. It runs to 30 seconds and stops at 720p. We work through what it's best at, what a clip costs at each resolution, how it compares to Seedance 2.0, Wan 3.0, and Veo 3.1 on our own catalog data, and the cases where we'd recommend a different model.Wed, 09 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/us-in-region-routing/https://openrouter.ai/blog/announcements/us-in-region-routing/US In-Region Routing is live, joining the EU. Send requests to us.openrouter.ai and they are decrypted only inside the United States and served only by providers running there, across models from OpenAI, Anthropic, Google, NVIDIA, Thinking Machines, DeepSeek, Moonshot, and Qwen.Wed, 09 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/shell-tool/https://openrouter.ai/blog/announcements/shell-tool/The shell server tool gives any model on OpenRouter a hosted Linux shell, and the Files API moves files in and out of it. Commands run in an isolated container, the model reads back stdout, stderr, and exit codes, and files the run writes can be downloaded afterward. Available today in beta on the Responses and Messages APIs.Tue, 08 Sep 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/choose-best-ai-model/https://openrouter.ai/blog/tutorials/choose-best-ai-model/There's no single best AI model, only the best model for a given task, budget, and moment. This article describes a six-step framework for choosing one, and how to run every step from your editor through the OpenRouter MCP server.Tue, 25 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/gpt-5-6-discounts-jevons-paradox/https://openrouter.ai/blog/insights/gpt-5-6-discounts-jevons-paradox/OpenAI introduced large discounts on their new Terra and Luna models from July 27th through August 14th. What impact did these discounts have on token volumes, total spend, and the competition?Tue, 25 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/video-generation-api/https://openrouter.ai/blog/tutorials/video-generation-api/Every video provider has its own endpoint, job statuses, polling logic, and output format. Our async video API puts Seedance, Veo, Wan, and more behind one submit, poll, and download loop. Here's the full lifecycle in Python and TypeScript.Tue, 25 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/image-benchmarks/https://openrouter.ai/blog/announcements/image-benchmarks/We ran 39 image models through 15 deliberately hard prompts and put every result on one page. Compare fill levels, finger counts, poster text, and edits side by side, with the price and generation time under each image.Fri, 21 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/openrouter-is-joining-stripe/https://openrouter.ai/blog/announcements/openrouter-is-joining-stripe/Today, we are excited to announce that we are joining forces with Stripe, to power the next wave of GDP growth globally.Wed, 19 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/activity-dashboard/https://openrouter.ai/blog/announcements/activity-dashboard/See what your team spent on every model, save the charts you keep rebuilding, click any bar to land in the logs behind it, and query the same data from your terminal with the Analytics API.Mon, 17 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/image-generation/https://openrouter.ai/blog/tutorials/image-generation/Supporting more than one image provider means handling different endpoints, data formats, and billing models. Our dedicated Image API gives you one request format and one key across supported models. Here's the full prompt-to-local-file workflow in Python and JavaScript.Mon, 17 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/send-image-to-llm/https://openrouter.ai/blog/tutorials/send-image-to-llm/To get a model to read a screenshot, you need the right request body. This guide shows the content-array pattern that works across every vision-capable model we support, when to use base64 instead of a hosted URL, and how to build multimodal RAG on top of it.Fri, 14 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/tool-calling/https://openrouter.ai/blog/tutorials/tool-calling/Most tool-calling tutorials cover one provider, so you rewrite the loop when you switch. This guide shows the full loop in Python, JavaScript, and cURL, then runs it against three providers by changing one string.Wed, 12 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/web-search-benchmark/https://openrouter.ai/blog/announcements/web-search-benchmark/We published live leaderboards grading web search configurations across four task suites. Compare engines, search depth, and models by quality, cost, and speed before your agent makes its first search.Wed, 12 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/introducing-the-new-auto-router/https://openrouter.ai/blog/announcements/introducing-the-new-auto-router/Our new Auto router is informed by the model decisions of millions of people, and it outperforms conventional task-based classifiers across a wide spectrum of tasks.Mon, 10 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/team-spend-controls-setup/https://openrouter.ai/blog/tutorials/team-spend-controls-setup/OpenRouter has five controls for team spend: an organization with a shared credit pool, presets that scope models per workload, per-key spend caps, guardrails that enforce per-member budgets, and the Activity dashboard that shows who spent what. This guide sets them all up in one pass, in order.Fri, 07 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/governing-team-ai-spend/https://openrouter.ai/blog/insights/governing-team-ai-spend/Your team's AI bill is the total of every key each engineer holds. OpenRouter gives you six ways to control that spend, from per-key limits to Enterprise workspace budgets. This guide explains what each control caps, what plan it needs, and which ones fit your team.Thu, 06 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/ori-harness/https://openrouter.ai/blog/announcements/ori-harness/Using OpenRouter with your favorite harness usually means ad-hoc scripts or a wall of environment variables. Install the ori CLI, log in once, and every supported harness runs with an optimized configuration out of the box.Tue, 04 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/ori-eval/https://openrouter.ai/blog/announcements/ori-eval/Choosing the model inside your product is often decided without a systematic method. Ori Eval answers the question with proof: it runs your agent on your own prompts, checks the tools it called, and grades the answers.Mon, 03 Aug 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/langchain-chatopenrouter-setup/https://openrouter.ai/blog/tutorials/langchain-chatopenrouter-setup/The LangChain integration now has a dedicated package: langchain-openrouter on PyPI and @langchain/openrouter on npm. Most guides still teach the old ChatOpenAI base_url override. This is the current path, plus the routing economics the docs skip.Wed, 29 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/evaluate-llm-provider-performance/https://openrouter.ai/blog/insights/evaluate-llm-provider-performance/The same model behaves differently across provider endpoints. Infrastructure, quantization, load handling, and routing defaults all change the result. Here's how to measure latency, throughput, uptime, and precision, then turn the measurements into a routing policy.Tue, 28 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/image-generation-models/https://openrouter.ai/blog/tutorials/image-generation-models/Generation runs through the dedicated /api/v1/images endpoint and understanding through /chat/completions, with the same key and billing. Here's the full contract for both jobs, plus the fix for the 'no endpoints found' error.Mon, 27 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/classifiers/https://openrouter.ai/blog/announcements/classifiers/Define a taxonomy and a small model tags every generation in your workspace by department, task type, or agent complexity. Filter your logs and group your Activity analytics by the results.Fri, 24 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/transcription-on-openrouter/https://openrouter.ai/blog/tutorials/transcription-on-openrouter/Send base64 audio to POST /api/v1/audio/transcriptions and get JSON text plus a usage object back, with the same API key you already use for chat. Here's the full request contract, the model families, and the limits to design around.Wed, 22 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/prompt-caching-sticky-routing/https://openrouter.ai/blog/tutorials/prompt-caching-sticky-routing/Your agent sends the same system prompt, tool definitions, and schemas on every turn. Cache reads cost 0.1x to 0.5x of fresh input, but only if the next request lands on the provider holding the warm cache. Here's how caching and sticky routing work together, and how to confirm they're working.Tue, 21 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/every-modality-one-api/https://openrouter.ai/blog/insights/every-modality-one-api/Chat, image generation, embeddings, and transcription usually mean four SDKs, four bills, and four auth schemes. On OpenRouter every modality runs through one base URL: you change the model string and the content type, and the same routing controls carry across.Thu, 16 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/brand-refresh/https://openrouter.ai/blog/announcements/brand-refresh/Built from first principles and grounded in timeless Bauhaus philosophy, our new brand identity marks the beginning of our next chapter.Mon, 13 Jul 2026 15:00:00 GMThttps://openrouter.ai/blog/insights/why-openrouter-for-deepseek/https://openrouter.ai/blog/insights/why-openrouter-for-deepseek/DeepSeek is one model served by 16 providers, at prices that vary by about 4x and throughput from 4 to 57 tokens per second. Here's what routing that spread through one slug actually buys you, and when going direct is the better call.Mon, 13 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/image-detail-low-cost/https://openrouter.ai/blog/insights/image-detail-low-cost/We ran 1,730 visual reasoning questions across 5 models. Dropping image detail to "low" costs real accuracy, and on gpt-5.5 the bill went up too. The lever that reliably cuts cost is reasoning effort.Tue, 07 Jul 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/deepseek-v4-adoption/https://openrouter.ai/blog/insights/deepseek-v4-adoption/DeepSeek doubled its token share on OpenRouter in six months. V4 Flash is the model that made it happen, and agentic workloads are driving the surge.Tue, 30 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/the-open-weight-models-that-matter-june-2026/https://openrouter.ai/blog/insights/the-open-weight-models-that-matter-june-2026/A slew of compelling open-weight models have shipped from new players in both China and the US. As of June 2026, these are the four open-weight models that matter the most — and when to reach for each.Sat, 27 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/openrouter-mcp-server/https://openrouter.ai/blog/announcements/openrouter-mcp-server/Connect your coding agent to OpenRouter's live model catalog, benchmarks, docs, and test inference, all without leaving your editor.Thu, 25 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/image-api/https://openrouter.ai/blog/announcements/image-api/A dedicated Image API with capability discovery across 30+ models from 8 providers. One endpoint tells your code what each model can do.Tue, 23 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/ai-governance-checklist/https://openrouter.ai/blog/insights/ai-governance-checklist/Policy language can't show who called which model or where the audit trail lives. Map your governance checklist to the three routing postures your stack can actually prove.Mon, 22 Jun 2026 19:00:00 GMThttps://openrouter.ai/blog/insights/ai-data-residency/https://openrouter.ai/blog/insights/ai-data-residency/If your procurement team flagged country of origin, you don't need to build local infrastructure. For API teams, data residency is a routing constraint you enforce in a single request.Mon, 22 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/openrouter-vs-portkey/https://openrouter.ai/blog/insights/openrouter-vs-portkey/OpenRouter routes across providers on credits you buy; Portkey governs the provider keys you already have. Here's how they compare on models, observability, compliance, and price.Fri, 19 Jun 2026 19:00:00 GMThttps://openrouter.ai/blog/insights/openrouter-vs-litellm/https://openrouter.ai/blog/insights/openrouter-vs-litellm/OpenRouter is a managed gateway; LiteLLM is a self-hosted proxy. Here's how they compare on cost, data residency, routing, and latency.Fri, 19 Jun 2026 15:00:00 GMThttps://openrouter.ai/blog/tutorials/openclaw-openrouter/https://openrouter.ai/blog/tutorials/openclaw-openrouter/OpenClaw has built-in OpenRouter support. One command gives your agents one key, one bill, and automatic failover across 300+ models. Here's the setup and the fixes for the errors that trip people up.Thu, 18 Jun 2026 19:00:00 GMThttps://openrouter.ai/blog/tutorials/sillytavern-openrouter/https://openrouter.ai/blog/tutorials/sillytavern-openrouter/One OpenRouter key gives SillyTavern 300+ models in a single dropdown, many of them free to start. Here's the five-step connection, the roleplay models to try, and fixes for the errors users hit most.Thu, 18 Jun 2026 15:00:00 GMThttps://openrouter.ai/blog/tutorials/kilo-code-openrouter/https://openrouter.ai/blog/tutorials/kilo-code-openrouter/Kilo Code is a bring-your-own-provider coding agent, so adding OpenRouter gives it one key for 300+ models, provider routing, and failover. Here's the three-step setup plus the kilo.json fields that control routing.Wed, 17 Jun 2026 19:00:00 GMThttps://openrouter.ai/blog/tutorials/codex-cli-openrouter/https://openrouter.ai/blog/tutorials/codex-cli-openrouter/Codex CLI supports custom OpenAI-compatible providers, so a small config.toml block routes it through OpenRouter. You get provider failover, usage tracking, and one key across every model, with no change to Codex itself.Wed, 17 Jun 2026 15:00:00 GMThttps://openrouter.ai/blog/tutorials/claude-code-openrouter/https://openrouter.ai/blog/tutorials/claude-code-openrouter/Route Claude Code through OpenRouter with three environment variables and no local proxy. You get provider failover, budget controls, and usage visibility on top of the same Anthropic models.Tue, 16 Jun 2026 19:00:00 GMThttps://openrouter.ai/blog/tutorials/any-coding-agent/https://openrouter.ai/blog/tutorials/any-coding-agent/Any tool that speaks the OpenAI API works with OpenRouter after two changes, the base URL and the key. Here's the setup pattern and the tools that already support it.Tue, 16 Jun 2026 15:00:00 GMThttps://openrouter.ai/blog/announcements/subagent-server-tool/https://openrouter.ai/blog/announcements/subagent-server-tool/The openrouter:subagent server tool lets a frontier model hand off self-contained tasks to a smaller, cheaper, faster worker model mid-generation. Summarize a doc, extract structured data, reformat text, all without burning frontier tokens.Tue, 16 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/free-llm-apis-compared/https://openrouter.ai/blog/tutorials/free-llm-apis-compared/Stop guessing which free LLM API survives past a side project. Here's how OpenRouter, Groq, Gemini, and 10 more compare on limits, cost, and data use.Mon, 15 Jun 2026 17:00:00 GMThttps://openrouter.ai/blog/insights/agentic-ai-governance/https://openrouter.ai/blog/insights/agentic-ai-governance/Most agentic AI governance frameworks define the rules but never enforce them. Learn how the API routing layer stops runaway spend and model escalation.Mon, 15 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/tutorials/keep-your-agent-running-when-models-disappear/https://openrouter.ai/blog/tutorials/keep-your-agent-running-when-models-disappear/Anthropic restricted Claude Fable 5 just days after launch. If your code hard-codes a model slug, that becomes your outage too. Presets move model choice to the server so you can swap models, set fallbacks, and enforce a data policy without redeploying.Mon, 15 Jun 2026 12:00:00 GMThttps://openrouter.ai/blog/tutorials/hermes-agent/https://openrouter.ai/blog/tutorials/hermes-agent/Hermes Agent has pushed over 17 trillion tokens through OpenRouter. Here's how to set it up, pick a model that clears the 64K context bar, and tune routing for cost and reliability.Fri, 12 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/tutorials/how-to-get-the-lowest-cost-llm-inference-on-openrouter/https://openrouter.ai/blog/tutorials/how-to-get-the-lowest-cost-llm-inference-on-openrouter/Append :floor for the cheapest provider, cap spend with max_price, and start free with 20+ zero-cost models. Plus the billing gotchas to avoid.Fri, 12 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/insights/model-routing/https://openrouter.ai/blog/insights/model-routing/OpenRouter routes every request across 70+ providers, and you control how: provider order, price ceilings, and the fallback chain. Here's how each routing layer works.Fri, 12 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/insights/reliability-failover/https://openrouter.ai/blog/insights/reliability-failover/Provider failover is on by default. Model fallbacks are opt-in. The two layers recover from different failures; here's how each one works and where failover stops.Fri, 12 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/announcements/fusion-beats-frontier/https://openrouter.ai/blog/announcements/fusion-beats-frontier/A panel of budget models, fused through OpenRouter, outscored GPT-5.5 and Claude Opus 4.8 on 100 complex research tasks.Fri, 12 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/insights/dinner-is-served/https://openrouter.ai/blog/insights/dinner-is-served/Standardizing on one LLM is like everyone at the table ordering their own entree. The case for going family style with your AI, and the OpenRouter data showing teams already do.Thu, 11 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/insights/llm-gateway/https://openrouter.ai/blog/insights/llm-gateway/Without an LLM gateway, provider outages become user-facing errors and AI spend stays opaque. Compare the best options by routing, compliance, and setup time.Thu, 11 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/announcements/advisor-server-tool/https://openrouter.ai/blog/announcements/advisor-server-tool/The openrouter:advisor server tool lets a fast, cheap model consult a stronger one mid-generation. Run GPT-4o Mini for the routine work. Call Claude Fable when it actually matters.Wed, 10 Jun 2026 18:00:00 GMThttps://openrouter.ai/blog/tutorials/gemini-25-flash-api-pricing-quickstart-provider-comparison/https://openrouter.ai/blog/tutorials/gemini-25-flash-api-pricing-quickstart-provider-comparison/Overpaying for reasoning you don't need? Learn how to configure Gemini 2.5 Flash API thinking budgets, compare providers, and make your first call in 5 minutes.Tue, 09 Jun 2026 16:00:00 GMThttps://openrouter.ai/blog/tutorials/human-oversight-eu-ai-act-compliance-agent-sdk/https://openrouter.ai/blog/tutorials/human-oversight-eu-ai-act-compliance-agent-sdk/Use the Agent SDK's human-in-the-loop (HITL) tools to meet AI agent compliance requirements from the EU AI Act, Colorado's Automated Decision-Making Technology law (SB26-189), and NIST AI RMF.Mon, 08 Jun 2026 12:00:00 GMThttps://openrouter.ai/blog/insights/royale-last-agent-standing/https://openrouter.ai/blog/insights/royale-last-agent-standing/A 30-game battle royale across eleven LLMs, $482 of inference, and one finding that should change how you read model benchmarks.Thu, 04 Jun 2026 12:00:00 GMThttps://openrouter.ai/blog/announcements/may-release-spotlight/https://openrouter.ai/blog/announcements/may-release-spotlight/Speech and transcription APIs, Model Fusion, private models, enterprise workspace controls, and 20 new model launches including Gemini 3.5 Flash and Claude Opus 4.8.Mon, 01 Jun 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/guardrails/https://openrouter.ai/blog/announcements/guardrails/Configurable security and governance tools for budget enforcement, zero data retention, model and provider restrictions, prompt injection defense, and data loss prevention.Fri, 29 May 2026 12:00:00 GMThttps://openrouter.ai/blog/announcements/series-b/https://openrouter.ai/blog/announcements/series-b/OpenRouter has raised a $113M Series B led by CapitalG, with participation from NVentures, ServiceNow Ventures, MongoDB Ventures, Snowflake Ventures, Databricks Ventures, AMP PBC, and Pace Capital, alongside existing investors Andreessen Horowitz and Menlo Ventures.Thu, 28 May 2026 14:00:00 GMThttps://openrouter.ai/blog/tutorials/human-in-the-loop-tools/https://openrouter.ai/blog/tutorials/human-in-the-loop-tools/A new tool type in the OpenRouter Agent SDK lets your agent auto-resolve routine decisions and pause for human input on high-stakes ones, with two hooks and zero loop-management code.Fri, 08 May 2026 12:00:00 GMThttps://openrouter.ai/blog/announcements/agentic-web-tools/https://openrouter.ai/blog/announcements/agentic-web-tools/Give any tool-calling model the ability to search the web and fetch page content on its own, with multiple search engines and fetch engines to choose from.Thu, 07 May 2026 12:00:00 GMThttps://openrouter.ai/blog/insights/gpt55-cost-analysis/https://openrouter.ai/blog/insights/gpt55-cost-analysis/OpenAI doubled per-token prices with GPT-5.5 but the model is less verbose. We measured real usage to see the net cost impact.Mon, 04 May 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/announcing-audio-apis/https://openrouter.ai/blog/announcements/announcing-audio-apis/Text-to-speech and transcription are now live on OpenRouter. Two new endpoints give you access to speech synthesis and audio transcription across multiple providers, under one API.Fri, 01 May 2026 18:00:00 GMThttps://openrouter.ai/blog/announcements/response-caching/https://openrouter.ai/blog/announcements/response-caching/Introducing the new Response Caching header: enables caching identical API requests so responses come back in a tiny fraction of the time, at zero cost.Thu, 30 Apr 2026 18:00:00 GMThttps://openrouter.ai/blog/announcements/april-release-spotlight/https://openrouter.ai/blog/announcements/april-release-spotlight/Video generation, workspaces, an agent SDK, reranker models, and a wave of frontier model launches.Thu, 30 Apr 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/openrouter-on-stripe-projects/https://openrouter.ai/blog/announcements/openrouter-on-stripe-projects/Run `stripe projects add openrouter/api` to get an OpenRouter account, an API key, and Stripe billing, all from the command line. Your agents can do it too.Wed, 29 Apr 2026 12:00:00 GMThttps://openrouter.ai/blog/insights/opus-47-tokenizer-analysis/https://openrouter.ai/blog/insights/opus-47-tokenizer-analysis/Anthropic changed the tokenizer in Opus 4.7. We looked at usage that shifted from 4.6 to 4.7 to measure exactly how it affects costs.Mon, 27 Apr 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/agent-sdk-with-callmodel/https://openrouter.ai/blog/tutorials/agent-sdk-with-callmodel/The OpenRouter Agent SDK gives you callModel: one function that turns a chat completion into a multi-step agent with tool calls, stop conditions, and cost tracking across 400+ models.Fri, 24 Apr 2026 12:00:00 GMThttps://openrouter.ai/blog/tutorials/create-agent-harness-with-agent-sdk/https://openrouter.ai/blog/tutorials/create-agent-harness-with-agent-sdk/Use the create-agent-tui and create-headless-agent skills to scaffold a personalized coding agent in minutes — with a terminal UI or headless for scripts and pipelines.Fri, 24 Apr 2026 12:00:00 GMThttps://openrouter.ai/blog/announcements/introducing-workspaces/https://openrouter.ai/blog/announcements/introducing-workspaces/Organize your OpenRouter projects into separate environments, each with its own API keys, routing defaults, guardrails, and observability.Wed, 22 Apr 2026 12:00:00 GMThttps://openrouter.ai/blog/announcements/video-generation/https://openrouter.ai/blog/announcements/video-generation/Video generation is now live on OpenRouter. One API gives you access to the top video models.Wed, 15 Apr 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/auto-exacto/https://openrouter.ai/blog/announcements/auto-exacto/Auto Exacto re-evaluates providers every 5 minutes across throughput, tool-call telemetry, and benchmark scores. For requests that include tools, it's on by default.Thu, 12 Mar 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/february-release-spotlight/https://openrouter.ai/blog/announcements/february-release-spotlight/Benchmarks on model pages, a new free model router, and improved cost transparency between providers. Mon, 23 Feb 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/openrouter-outages-on-february-17-and-19-2026/https://openrouter.ai/blog/announcements/openrouter-outages-on-february-17-and-19-2026/What happened and what have we done to prevent this happening again? Fri, 20 Feb 2026 00:00:00 GMThttps://openrouter.ai/blog/announcements/january-release-spotlight/https://openrouter.ai/blog/announcements/january-release-spotlight/Prioritize fast LLMs, explore providers, customize the auto router, load skills in the SDK, and big performance improvements. Fri, 09 Jan 2026 00:00:00 GMThttps://openrouter.ai/blog/tutorials/distillable-models-and-synthetic-data-pipelines-with-nemo-data-designer/https://openrouter.ai/blog/tutorials/distillable-models-and-synthetic-data-pipelines-with-nemo-data-designer/How to generate license-safe synthetic data workflows for model specialization Wed, 24 Dec 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/december-release-spotlight/https://openrouter.ai/blog/announcements/december-release-spotlight/Response Healing for structured outputs, chatroom notifications, long-context model rankings, and we're #1 on Brex's fastest-growing AI infra list! Thu, 18 Dec 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/response-healing-reduce-json-defects-by-80percent/https://openrouter.ai/blog/announcements/response-healing-reduce-json-defects-by-80percent/Today we're launching Response Healing, a new feature on OpenRouter that automatically fixes malformed JSON responses from LLMs before they reach your application Thu, 18 Dec 2025 00:00:00 GMThttps://openrouter.ai/blog/insights/the-2025-state-of-ai-report/https://openrouter.ai/blog/insights/the-2025-state-of-ai-report/Introducing the 2025 State of AI report, in partnership with a16z. The largest empirical look yet at how developers and organizations use language models in the real world. Thu, 04 Dec 2025 00:00:00 GMThttps://openrouter.ai/blog/insights/is-implicit-caching-prompt-retention/https://openrouter.ai/blog/insights/is-implicit-caching-prompt-retention/Should customers consider providers that have implicit caching as “ZDR”? Thu, 23 Oct 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/provider-variance-introducing-exacto/https://openrouter.ai/blog/announcements/provider-variance-introducing-exacto/Does the same model perform differently across different providers? Tue, 21 Oct 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/1-million-free-byok-requests-per-month/https://openrouter.ai/blog/announcements/1-million-free-byok-requests-per-month/An October 2025 update to OpenRouter's “Bring Your Own Key” (BYOK) platform fee.Wed, 01 Oct 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/the-first-ever-image-model-is-up-on-openrouter/https://openrouter.ai/blog/announcements/the-first-ever-image-model-is-up-on-openrouter/SOTA image generation, character consistency, and multi-image outputs—now live with Gemini 2.5 Flash Image Preview. Tue, 26 Aug 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/gpt-5-is-now-live/https://openrouter.ai/blog/announcements/gpt-5-is-now-live/GPT-5 is here on OpenRouter — long-context, built for complex reasoning and code workflows. Thu, 07 Aug 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/audio-inputs-and-pdf-urls-for-apps/https://openrouter.ai/blog/announcements/audio-inputs-and-pdf-urls-for-apps/Add voice input and send PDFs by URL, on any model. Mon, 04 Aug 2025 00:00:00 GMThttps://openrouter.ai/blog/tutorials/presets-how-to-seamlessly-transfer-model-configurations-across-apps/https://openrouter.ai/blog/tutorials/presets-how-to-seamlessly-transfer-model-configurations-across-apps/Customize once and use everywhere. Server-side presets now simplify your model workflows. Tue, 29 Jul 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/new-privacy-focused-provider-drop-venice/https://openrouter.ai/blog/announcements/new-privacy-focused-provider-drop-venice/Venice joins OpenRouter as a new provider, offering its flagship uncensored model for private, powerful, and non-restrictive AI. Tue, 15 Jul 2025 00:00:00 GMThttps://openrouter.ai/blog/tutorials/use-openrouter-models-in-cursor-try-it-with-moonshot-ais-kimi-k2/https://openrouter.ai/blog/tutorials/use-openrouter-models-in-cursor-try-it-with-moonshot-ais-kimi-k2/Explore it in action: See how effortlessly you can run Kimi K2 in Cursor using OpenRouter’s flexible model routing. Mon, 14 Jul 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/updates-to-our-free-tier-sustaining-accessible-ai-for-everyone/https://openrouter.ai/blog/announcements/updates-to-our-free-tier-sustaining-accessible-ai-for-everyone/Introducing new models to sustain accessible AI inference. Thu, 10 Jul 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/new-stealth-model-cypher-alpha/https://openrouter.ai/blog/announcements/new-stealth-model-cypher-alpha/Try Cypher Alpha — a free, general-purpose stealth model with built-in tool-calling. Tue, 01 Jul 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/introducing-presets-manage-llm-configs-from-your-dashboard/https://openrouter.ai/blog/announcements/introducing-presets-manage-llm-configs-from-your-dashboard/Centralize your LLM logic, iterate faster, and clean up your code. Presets are now live on OpenRouter. Thu, 26 Jun 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/dev-and-byok-updates-uptime-api-smarter-key-management/https://openrouter.ai/blog/announcements/dev-and-byok-updates-uptime-api-smarter-key-management/Track model uptime via API and get more control over your BYOK setup including usage limits and testable keys. Wed, 25 Jun 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/simplifying-our-platform-fee/https://openrouter.ai/blog/announcements/simplifying-our-platform-fee/We’re rolling out a simpler and more transparent platform fee structure: Mon, 09 Jun 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/gif-prompts-omni-search-tool-caching-and-byok-flags/https://openrouter.ai/blog/announcements/gif-prompts-omni-search-tool-caching-and-byok-flags/Faster workflows, smarter tooling, and smoother image support—GIFs, provider search, Anthropic tool-call caching, and BYOK confirmation are all now live. Wed, 04 Jun 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/new-features-reasoning-streams-crypto-invoices-end-user-ids-and-more/https://openrouter.ai/blog/announcements/new-features-reasoning-streams-crypto-invoices-end-user-ids-and-more/Stream reasoning summaries, protect your rate limits, pay with crypto, and lock down your keys—now all live on OpenRouter. Wed, 28 May 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/passkeys-devex-upgrades-and-a-new-guide-for-typescript-agents/https://openrouter.ai/blog/announcements/passkeys-devex-upgrades-and-a-new-guide-for-typescript-agents/Secure your account with passkeys, explore provider slugs, and build agents faster with fresh docs. Thu, 22 May 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/new-provider-drop-cerebras-is-here/https://openrouter.ai/blog/announcements/new-provider-drop-cerebras-is-here/A provider built for speed and scale—from wafer to token. See what becomes possible when memory bottlenecks disappear. Wed, 07 May 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/better-insights-faster-metrics-and-new-developer-power-tools/https://openrouter.ai/blog/announcements/better-insights-faster-metrics-and-new-developer-power-tools/Deeper usage insights, sharper perf metrics, and new dev tools to speed up your workflow. Tue, 06 May 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/privacy-clarity-new-providers-oauth-upgrade-and-gemini-gets-parallel-tools/https://openrouter.ai/blog/announcements/privacy-clarity-new-providers-oauth-upgrade-and-gemini-gets-parallel-tools/A couple quality-of-life improvements for developers! Mon, 28 Apr 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/universal-pdf-support/https://openrouter.ai/blog/announcements/universal-pdf-support/OpenRouter now supports PDF processing for every model. Wed, 23 Apr 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/smarter-charts-inline-svgs-and-live-usage-accounting/https://openrouter.ai/blog/announcements/smarter-charts-inline-svgs-and-live-usage-accounting/Smarter analytics, smoother previews, and instant cost visibility—all now live on OpenRouter. Fri, 18 Apr 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/quasar-alpha-and-optimus-alpha-reveal/https://openrouter.ai/blog/announcements/quasar-alpha-and-optimus-alpha-reveal/Quasar Alpha and Optimus Alpha, which both topped the charts during testing, were early test versions of... Mon, 14 Apr 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/stealth-model-optimus-alpha/https://openrouter.ai/blog/announcements/stealth-model-optimus-alpha/Announcing our second "stealth" model Optimus Alpha Thu, 10 Apr 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/stealth-model-quasar-alpha/https://openrouter.ai/blog/announcements/stealth-model-quasar-alpha/Announcing our first-ever “stealth” model, Quasar Alpha Thu, 03 Apr 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/never-pay-for-empty-ai-responses-again/https://openrouter.ai/blog/announcements/never-pay-for-empty-ai-responses-again/Introducing Zero Token Insurance for All Models Tue, 25 Mar 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/deep-research-and-many-new-models/https://openrouter.ai/blog/announcements/deep-research-and-many-new-models/The first deep research tool available through the OpenRouter API is live, with full citations directly in the API response. Thu, 06 Mar 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/introducing-nitro-and-floor-price-shortcuts/https://openrouter.ai/blog/announcements/introducing-nitro-and-floor-price-shortcuts/We're rolling out new sorting shortcuts to give you more control over how OpenRouter selects providers Wed, 12 Feb 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/introducing-cloudflare-as-a-new-provider/https://openrouter.ai/blog/announcements/introducing-cloudflare-as-a-new-provider/Clouldflare is live now with a new to OpenRouter Gemma model + popular Llama models. Tue, 04 Feb 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/reasoning-tokens-for-thinking-models/https://openrouter.ai/blog/announcements/reasoning-tokens-for-thinking-models/Understand model thought processes with reasoning tokens Fri, 24 Jan 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/introducing-web-search-via-the-api/https://openrouter.ai/blog/announcements/introducing-web-search-via-the-api/Bring all of your requests up to speed with the latest information by incorporating web search results. Thu, 23 Jan 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/standardized-finish-reasons/https://openrouter.ai/blog/announcements/standardized-finish-reasons/Models now return standardized finish reason values, aligned with OpenAI-style conventions. Thu, 23 Jan 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/happy-new-year-introducing-a-new-auto-router/https://openrouter.ai/blog/announcements/happy-new-year-introducing-a-new-auto-router/To start off 2025, we have an upgrade to the Auto Router, and a partnership with NotDiamond Wed, 01 Jan 2025 00:00:00 GMThttps://openrouter.ai/blog/announcements/holiday-launches-web-search-and-price-cuts/https://openrouter.ai/blog/announcements/holiday-launches-web-search-and-price-cuts/Web search is available for free in the OpenRouter Chatroom. Tue, 24 Dec 2024 00:00:00 GMThttps://openrouter.ai/blog/announcements/bring-your-own-api-keys/https://openrouter.ai/blog/announcements/bring-your-own-api-keys/Combine your provider limits and/or cloud credits with OpenRouter, and unify your analytics. Fri, 20 Dec 2024 00:00:00 GMThttps://openrouter.ai/blog/announcements/crypto-payments-api/https://openrouter.ai/blog/announcements/crypto-payments-api/The first way to script on-chain payments for any LLM 💸 Fri, 20 Dec 2024 00:00:00 GMThttps://openrouter.ai/blog/announcements/structured-outputs-and-free-gemini-flash-20/https://openrouter.ai/blog/announcements/structured-outputs-and-free-gemini-flash-20/Structured outputs for OpenAI 4o and Fireworks models + Gemini Flash 2.0 Thu, 12 Dec 2024 00:00:00 GMThttps://openrouter.ai/blog/announcements/price-drops-and-llama-33-70b/https://openrouter.ai/blog/announcements/price-drops-and-llama-33-70b/Price drops and six models, and providers for Llama 3.3 70b Fri, 06 Dec 2024 00:00:00 GMThttps://openrouter.ai/blog/announcements/author-pages-and-amazon-nova/https://openrouter.ai/blog/announcements/author-pages-and-amazon-nova/The new Nova family of models from Amazon has arrived. Thu, 05 Dec 2024 00:00:00 GMT