Blog
Guides, comparisons, and engineering notes from the team building AnyRouter — one OpenAI-compatible endpoint in front of every model.
Changelog
New models added to the catalog — frontier releases as they land.
- 2026-10-19MiniMax M3.1 FlashMiniMax's multimodal agent and coding model joins the catalog, free to call.MiniMax M3.1 Flash
- 2026-10-17LFM 2.5 24B A2BLiquid AI's open-weight reasoning MoE joins the catalog, BYOK through OpenRouter and Vercel.LFM 2.5 24B A2B
- 2026-10-17Xing4.0 29B A4BChina Telecom TeleAI's open-weight reasoning MoE joins the catalog, free to call.Xing4.0 29B A4B
Guides
How to route every model through one OpenAI-compatible endpoint — setup, coding agents, MCP, free models, and BYOK.
- October 16, 2026Run Claude Code on free models in two linesInstall the anyr CLI, then run anyr claude. Claude Code works on AnyRouter's free models with no card. Exact commands, the manual setup, which models to try, and the limits.
- September 1, 2026Claude Code on anyrouter.devClaude Code on anyrouter.dev. setup.sh then anyr claude. ANTHROPIC_BASE_URL=https://anyrouter.dev/api. Free has no monthly credits; Go is $2/mo ($2.63 charged) → $4.
- August 19, 2026Use OpenCode with AnyRouter — CLI launcher or opencode.jsonPoint the OpenCode coding agent at AnyRouter in one command, or add a custom Chat Completions provider in opencode.json. One sk-ar- key reaches every catalog model, with unified billing and request logs.
- August 5, 2026Run Claude Code on AnyRouter — wrapper script or CLIRoute Claude Code through AnyRouter in two ways: a wrapper that installs itself and maps Opus, Sonnet, and Haiku to one catalog model (override with --model), or the anyr CLI launcher. One key, unified billing, audit logs.
- July 19, 2026Sign in with AnyRouter: let users bring their own LLM accountIf your app needs an LLM API to run, you have two bad options: ship your own keys and eat every user's inference bill, or make each user paste in a raw provider key. "Sign in with AnyRouter" is the third option — users sign in with their AnyRouter account, and their own balance powers the inference. You get a temporary, inference-only key per user and never handle model billing.
- July 19, 2026Run the Claude Agent SDK on any modelThe Claude Agent SDK reads ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY, the same two variables Claude Code uses. Point them at AnyRouter and every catalog model is available to query() behind the Anthropic /messages dialect — in TypeScript or Python.
- July 19, 2026Use AnyRouter with the Vercel AI SDK@anyr/ai-sdk-provider wraps the AnyRouter gateway as a standard Vercel AI SDK provider. Call createAnyRouter(), pass a provider/model id, and generateText, streamText, and generateObject work unchanged — switching models is a one-string edit.
- July 19, 2026Get a free NVIDIA API key and route it through one URLNVIDIA hands out a free API key with credits and no card required. Attach it to AnyRouter as BYOK and every NVIDIA-hosted model runs through one OpenAI-compatible endpoint — at $0 markup. Here's the five-minute setup.
- July 18, 2026Set up a Hermes agent with AnyRouterRun Nous Research's Hermes 3 405B as an agent in about three minutes: grab a free Hugging Face token, attach it as BYOK, mint an AnyRouter key, and point any OpenAI-compatible client at one URL. No markup, and donating idle quota earns 8% back.
- July 12, 2026Point Claude Code at a custom base URLClaude Code reads ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY, so pointing it at AnyRouter takes two environment variables — no plugin, no fork. You get every model in the catalog behind the same key, automatic failover when a provider is rate-limited, and one audit log shared with Codex, Cursor, and every other agent you run.
- July 12, 2026Use the OpenAI SDK with any modelThe official openai package for Python and TypeScript doesn't have to mean OpenAI models. Override base_url and api_key, keep every other call the same, and address 170+ models across 28+ providers as provider/model strings — including OpenAI's own.
- July 12, 2026Cheapest LLM API: how to actually shop for cost per tokenThe cheapest LLM API isn't the one with the lowest sticker price — it's the one with no markup added on top of it, a free tier that covers real usage, and a path to route on provider keys you already pay for. Here's how to actually compare cost instead of a headline number.
- July 12, 2026Free LLM API access for students and side projectsYou don't need a company card to build with real models. Between a no-spend free tier, a $2/mo plan if you outgrow it, and routing on free-tier keys you may already have from providers like Google AI Studio, there's a durable way to stay at $0 while a class project or side hustle is still finding its shape.
- July 12, 2026MCP servers for AI agents: what they are and how to connect oneAn MCP server lets an AI agent call a workspace's tools — keys, credits, models, status — over one standard interface instead of custom glue code per service. Here's what MCP is and how to connect AnyRouter's managed MCP server to Claude Desktop, Claude Code, Cursor, or your own agent.
- July 12, 2026One API for every LLMOne OpenAI-compatible endpoint reaches every model in the catalog — 170+ models addressed as provider/model, with automatic failover across upstreams, routing presets, and streaming. Point your existing client at AnyRouter and change a model with a string, not a rewrite.
- July 12, 2026BYOK: bring your own keys to every providerAttach the OpenAI, Anthropic, Google, and 60+ other provider keys you already pay for, route them through one OpenAI-compatible URL at $0 markup, cap spend per key, and — if you donate idle quota to the shared pool — earn up to 8% back and unlock Go for free while a donated key stays active.
- July 12, 2026Run coding agents through one gatewayPoint Claude Code, Codex, OpenCode, Cursor, or any OpenAI-compatible tool at AnyRouter and get one key for every model, unified billing, per-request audit logs, and app attribution. Two environment variables — or one npx command with the anyr CLI launcher.
- July 12, 2026An MCP gateway with managed server accessAnyRouter runs a Model Context Protocol server that exposes your workspace — models, keys, presets, credits, and status — as JSON-RPC tools, with OAuth 2.1 auth and a dashboard MCP Gateway for managed access. One endpoint any MCP client can connect to.
- July 12, 2026A unified AI API: one endpoint, every provider dialectOpenAI ships /chat/completions, Anthropic ships /messages, OpenAI's newer surface is /responses. A unified AI API speaks all of them at one URL, so the client library you already use keeps working — you swap the base URL, not the code.
- July 12, 2026The top website for free LLM models — and how they're actually freeAnyRouter serves a real free LLM API across 170+ catalog models. Here's what people actually route to for free, and the three honest mechanisms that make it free: the anyrouter/free tier, the donated shared pool, and self-hosted on-device models.
- July 12, 2026Free models, just $2 a monthAnyRouter's Go plan is $2/mo: a $4 monthly credit for paid models. Free models work on every plan. You can also donate a provider key so Go costs nothing, use anyrouter/free on any plan, or run models on your own device via local relay.
Comparisons
How AnyRouter stacks up against calling providers directly or through another gateway — pricing, markup, and lock-in.
- October 16, 2026AnyRouter vs OpenRouter: a sourced comparison and migration guideFees, BYOK, free-model limits and plans for AnyRouter and OpenRouter, each OpenRouter figure linked to its source and dated. Plus the base URL and key swap to move over.
- July 12, 2026Calling providers directly vs. routing through one gatewayCall OpenAI, Anthropic, and every other provider directly and you manage a key, an SDK, and an audit trail per provider. Route the same calls through one gateway and you manage one of each — at the cost of an extra hop. Here's the honest trade-off on auth, SDKs, failover, billing, audit logs, and switching cost.
- July 12, 2026An LLM API without vendor lock-inVendor lock-in with an LLM API usually isn't the model — it's the proprietary client shape you built against. Standing on the standard OpenAI-compatible surface (plus Anthropic /messages and OpenAI /responses) keeps the exit door open: the same code you write also works pointed straight at the origin provider.
- July 12, 2026An OpenAI API alternative that keeps your OpenAI codeLooking for an OpenAI-compatible API alternative? Keep your OpenAI SDK and code — swap one base URL and get every provider (including OpenAI itself), automatic failover, and $0-markup BYOK on the keys you already pay for.
- July 12, 2026OpenRouter alternatives 2026: how AnyRouter differsOpenRouter alternatives 2026, without invented rankings: AnyRouter is one OpenRouter alternative with $0-markup BYOK, a donated shared pool, a $2/mo Go plan, Cloudflare-edge routing, on-device models via local relay, a built-in MCP server, and open pricing config.
Product
New features, launches, and changes to the gateway — credits, the shared key pool, on-device models, and the dashboard.
- October 16, 2026Introducing the AnyRouter PoolThe AnyRouter Pool is a set of provider keys that members donate and the gateway shares, so free models keep answering for paid-plan members and donors when a single key runs dry. Here is who can donate, how a key is protected, how requests are spread across keys, what happens when a key fails, and how to stop.
- October 19, 2026How we protect your provider keysHow AnyRouter stores and uses the provider keys you add (BYOK) and the keys donated to the Pool: encryption at rest, who can read them, where they can be sent, what stays out of logs, and how to revoke one.
- October 10, 2026New models, 20 Sep – 10 Oct 2026Claude Haiku 5.5, five new Decisions models, GLM-5.3 Prime, Xiaomi MiMo V2.6 and more — new models from the last three weeks, with a release note for each.
- October 10, 2026Where every -latest alias points todayAnyRouter has 19 family aliases like google/gemini-flash-latest and z-ai/glm-latest. Here is the model each one resolves to on October 10, 2026, and the seven you can call on live routes right now.
- October 1, 2026Six decision models, two of them freeAnyRouter lists six System One decision models. Liquid d1 and Respan Span-01 Lite are priced at $0. The other four have a paid list rate and run on your own provider key.
- September 30, 2026Latest aliases: name a family, always get a live modelModels get retired or go down. A -latest alias calls the newest model in a family that is available right now, skips dead ones, and bills the model that answered.
- September 25, 2026anyr decision puts structured decisions in your terminalRun TypeSafe Jev, Fastino GLiNER2.5-Decide, or the anyrouter/decision preset with one native CLI command instead of forcing decision models through a chat agent.
- September 24, 2026Jev Decisions is now on its model pageJev turns application state and typed questions into structured answers with probabilities. Try the new model-page demo, the full Decisions app, or the playground.
- September 24, 2026Space Bunny Alpha is free on AnyRouterThe anonymous stealth preview is live with a 1M-token context, adjustable reasoning, multimodal input, and $0/$0 catalog routes while it is cloaked.
- September 9, 2026A shared key pool, and a free-token pool on the other sideAnyRouter started as one URL in front of many models. The part that actually matters is the pool: people donate spare provider keys, the gateway routes around them, and everyone else draws a free-token pool instead of hunting for a working key.
- September 1, 2026Donate a key for Go — no cardTwo ways to Go: pay $2/mo (card charged $2.63, $4 credits) or donate one eligible BYOK key (DeepSeek, Z.ai GLM, Moonshot Kimi). No Alipay or WeChat. Donor cut 5%/8%, capped at $1 per key per UTC day — that $1 is the donor cap, not the Go price.
- September 1, 2026AnyRouter pricing: Free vs Go (the $1 posts are wrong)Older pages still say $1 Go — wrong. Free has no monthly credits; anyrouter/free has no daily cap. Go is $2/mo ($2.63 charged) → $4. Pro $10 ($11.05) → $20; Pro+ $45 ($47.89) → $100; Max $100 ($105.79) → $300.
- August 26, 2026Ox Alpha is now GLM-5.3-FlashThe Ox Alpha preview is GLM-5.3-Flash: native multimodal, 1M context, MIT-licensed 320B-A18B. Same AnyRouter routes, new catalog id z-ai/glm-5.3-flash.
- August 20, 2026Qwen3.8-27B and DeepSeek V4 Flash, 50% offHalf off through 1 Sep. Same API, same model ids — just a friendlier bill.
- August 16, 2026CLI update: multiple accounts, terminal key management, and agents that delegateThe AnyRouter CLI now handles several accounts side by side, manages API keys without the dashboard, runs plan-then-implement pipelines across two models, and lets coding agents hand tasks to each other — one hop, one key.
- August 4, 2026Bring your CommandCode credential to AnyRouterThe CLI now reads your local CommandCode auth file and uploads it as a BYOK key — one command, no copy-paste.
- July 25, 2026Bring your Antigravity credential to AnyRouterA CLI that finds your local Antigravity credential, shows you exactly what it found, and uploads it as a BYOK key — with pool donation as a separate, explicit opt-in.
- July 11, 2026Apple's on-device Foundation Model, now on the AnyRouter APIRun Apple Intelligence's on-device Foundation Model on your own Mac and call it through the same AnyRouter API you use for everything else. Your prompts stay on your hardware, you pay nothing for tokens, and there's no vendor account to manage.
- July 11, 2026Go on AnyRouter for $2 — or free if you donate a keyGo is now $2/mo: a $4 monthly credit plus shared-pool access (free models work on every plan), no card surprises. Donate one working provider key to the shared pool instead, and Go costs nothing at all.
- June 29, 2026Donate an idle provider key, earn credits back: a walkthroughHold a provider key with headroom to spare? Donate it to the shared pool in two clicks. Every token the pool serves through your key earns pending credits — up to 8% of its notional cost, tiered by plan — claim them anytime or turn on auto-claim. Here's the step-by-step.
- June 28, 2026Bring your own keys — every provider behind one APIConnect the provider keys and subscriptions you already pay for, route them through one OpenAI-compatible URL with automatic failover, and — soon — earn credits back by donating idle quota to the shared pool.
- June 22, 2026A clearer way to pay: Free, Standard, and pay-as-you-goWe split billing into a simple subscription tier and separate pay-as-you-go credits, so you always know what you're paying for and what each request costs.
Data
What the traffic actually shows — most-used models, real latency, and the economics of running a router.
- October 10, 2026AnyRouter in October 2026: new models, top usage, free routesA snapshot of the live catalog and the last 30 days of traffic: the newest models, what people route most, the anyrouter/* router ids, what is free right now, and one tip.
- July 12, 2026What developers actually route through AnyRouterThe catalog has 170+ models across 28+ providers, but that's not what traffic looks like. A handful of models absorb almost all of the free-tier volume, model counts skew hard toward a few owner organizations, and most requests never mention a provider name at all — they arrive tagged by which coding agent sent them. Here's the shape of the catalog and the shape of what people actually call.
- July 11, 2026The most-used free models on AnyRouter so farWe pulled real usage from the gateway: which free models people actually route to. GLM-5.2 runs away with it, gpt-4o-mini is the workhorse behind it, and anyrouter/free quietly serves the long tail. Numbers below, straight from production.
Engineering
How the gateway is built on Cloudflare Workers — routing, failover, streaming, and the edge trade-offs behind it.
- July 12, 2026How automatic failover works in an LLM gatewayA single provider call has a single point of failure: one rate limit, one outage, one bad deploy on their end, and your request fails. Here's the actual mechanism AnyRouter uses to route around that — circuit breakers, escalating cooldowns, and a fallback chain — and why the extra hop barely registers next to model generation time.
- July 12, 2026Building an LLM gateway on Cloudflare WorkersAnyRouter runs as a set of Cloudflare Workers, not a long-running server. That constrains the design in specific ways — a 128MB memory ceiling that rules out buffering responses, a 3MiB script cap that forced a multi-Worker split, and a hard rule that every upstream call goes through Cloudflare's AI Gateway. Here's what that architecture actually looks like.