# AnyRouter > AnyRouter is a universal AI model router — one OpenAI-compatible API gateway that routes to 200+ models across 17+ providers, with unified billing, audit logs, and real-time pricing. ## When to use - Use AnyRouter when you need **one OpenAI-compatible endpoint for many models** — swap providers or models by changing a model id, not your client code. - Use it when you run **coding agents** (Claude Code, Codex, OpenCode) and want one API key, unified billing, usage logs, and automatic failover across upstreams. - Use it when you want **bring-your-own-key (BYOK)**: keep provider keys and route them behind the same gateway for failover and logging. - Use it for **text generation, embeddings, and OCR extraction** via Chat Completions (`POST /api/v1/chat/completions`), Messages (`POST /api/v1/messages`), Responses (`/api/v1/responses`), and Embeddings (`POST /api/v1/embeddings`). - Do not use it for **image or video generation** — the catalog is text and embeddings only. - If you call exactly one provider's SDK directly and never change models, a direct provider integration may be simpler. This index lists every doc page available as markdown for direct LLM consumption. Each link points to the raw markdown version of that page. ## Getting Started - [Quickstart](https://anyrouter.dev/docs/getting-started/quickstart.md): Make your first AnyRouter request in under five minutes by pointing any OpenAI-compatible client at one base URL. - [Authentication](https://anyrouter.dev/docs/getting-started/authentication.md): Generate, scope, and rotate AnyRouter API keys — bearer tokens, per-environment isolation, and bring-your-own-key. ## CLI & SDK - [AnyRouter CLI](https://anyrouter.dev/docs/cli.md): Launch Claude Code, Codex, and other coding agents through AnyRouter with one command — one key, automatic failover, unified billing. - [AnyRouter SDK](https://anyrouter.dev/docs/sdk.md): Official TypeScript SDK for the AnyRouter API — one key and one base URL for chat, embeddings, the Responses API, and the Anthropic Messages API, with a typed client and a Vercel AI SDK provider. - [anyr claude](https://anyrouter.dev/docs/cli/claude-code.md): Route Claude Code through AnyRouter for unified billing, audit logs, and a single API key that unlocks every model. One command via the AnyRouter CLI, or set two environment variables yourself. - [anyr codex](https://anyrouter.dev/docs/cli/codex.md): Route Codex through AnyRouter for unified billing, audit logs, and one key that reaches every model. One command via the AnyRouter CLI, or set two environment variables yourself. - [anyr opencode](https://anyrouter.dev/docs/cli/opencode.md): Route OpenCode through AnyRouter for unified billing, audit logs, and one key that reaches every model. One CLI command, or a custom provider in opencode.json. - [AnyRouter CLI Agent (deprecated)](https://anyrouter.dev/docs/agent.md): Deprecated — use anyr with Claude Code, Codex, or another launcher instead. - [Configuration](https://anyrouter.dev/docs/cli/configuration.md): Reference for the AnyRouter CLI — the config file, project-level anyrouter.yaml, profile fields, per-tool overrides, every CLI flag, and the management commands. - [Login with AnyRouter](https://anyrouter.dev/docs/cli/login.md): How the AnyRouter CLI signs you in — automatic browser login, device code on SSH, paste or key flags, and where credentials are stored. - [Plan and implement with anyr task](https://anyrouter.dev/docs/cli/task.md): Run a two-phase pipeline from the terminal — one model writes a step-by-step plan, a second model executes it. Pick a strong planner and a fast implementer to balance quality and cost. - [Accounts and keys in the CLI](https://anyrouter.dev/docs/cli/accounts-and-keys.md): Use several AnyRouter accounts side by side, see who you are signed in as, sign out cleanly, and manage API keys without leaving the terminal. - [Delegate tasks between coding agents](https://anyrouter.dev/docs/cli/delegate.md): Hand a task to Claude Code, Codex, or opencode headlessly from the terminal — or let a running agent delegate a subtask to another agent — all through one AnyRouter key. - [Usage, logs & transactions](https://anyrouter.dev/docs/cli/usage.md): See credits remaining, recent spend, request logs, and your credit ledger from the terminal with the AnyRouter CLI. - [CLI Changelog](https://anyrouter.dev/docs/cli/changelog.md): Release history for the AnyRouter CLI (anyr) — the launcher for Claude Code, Codex, Grok, and other coding agents. - [SDK Changelog](https://anyrouter.dev/docs/sdk/changelog.md): Release history for the AnyRouter TypeScript SDK (@anyr/sdk) and the Vercel AI SDK provider (@anyr/ai-sdk-provider). ## Guides - [Dashboard Tour](https://anyrouter.dev/docs/guides/dashboard-tour.md): A guided walkthrough of every dashboard page, in the order a new team typically uses them — from first API call to a governed, multi-seat account. - [Claude Code](https://anyrouter.dev/docs/guides/claude-code.md): Route Claude Code through AnyRouter for unified billing, audit logs, and a single API key that reaches every model — including GLM-5.2 with your own Z-AI key. - [Codex](https://anyrouter.dev/docs/guides/codex.md): Route Codex through AnyRouter for unified billing, audit logs, and one key that reaches every model — one CLI command, or two environment variables. - [OpenCode](https://anyrouter.dev/docs/guides/opencode.md): Point OpenCode at AnyRouter so every coding session uses one key, unified billing, and any Chat Completions model in the catalog. - [Hermes Agent](https://anyrouter.dev/docs/guides/hermes-agent.md): Run Nous Research's Hermes Agent against AnyRouter as a custom OpenAI-compatible provider — one key across every model, unified billing, and audit logs. - [OpenClaw](https://anyrouter.dev/docs/guides/openclaw.md): Run OpenClaw against AnyRouter — one key across every model and messaging channel, unified billing, and audit logs on every request. - [Cherry Studio](https://anyrouter.dev/docs/guides/cherry-studio.md): Connect Cherry Studio to AnyRouter — one API key across the whole catalog, unified billing, and audit logs, in a settings-only change. - [Get a provider API key](https://anyrouter.dev/docs/guides/byok-provider-keys.md): Step-by-step instructions for creating an API key at every BYOK-supported provider — where to sign up, the exact console page, the key format, and how to add it to AnyRouter. - [Pi](https://anyrouter.dev/docs/guides/pi.md): Run Pi against AnyRouter as a custom OpenAI-compatible provider — one key, unified billing, and any AnyRouter model from a single config file. - [Grok Bot, Herdr, and Anyr CLI](https://anyrouter.dev/docs/guides/grok-bot-herdr-anyr.md): Run coding work with Grok Bot assigning goals, Herdr showing the box, and Anyr CLI launching Claude Code when Cursor cloud is blocked. - [AI Agent Integration](https://anyrouter.dev/docs/guides/ai-agent-integration.md): Hand a coding agent everything it needs to wire AnyRouter into an existing project — base URL, key, and model ids. - [Streaming](https://anyrouter.dev/docs/guides/streaming.md): Receive completions incrementally via server-sent events to cut perceived latency and render tokens as they arrive. - [Using Responses API](https://anyrouter.dev/docs/guides/migrate-to-responses.md): Use AnyRouter's Responses endpoint for modern agent and tool workflows with structured output items. - [OpenAI](https://anyrouter.dev/docs/guides/migrate-from-openai.md): Move an OpenAI Chat Completions or Responses client to AnyRouter by changing the base URL, API key, and model id. - [Anthropic](https://anyrouter.dev/docs/guides/migrate-from-anthropic.md): Point Anthropic Messages clients at AnyRouter — change the base URL and key, keep the anthropic-version header. - [OpenRouter](https://anyrouter.dev/docs/guides/migrate-from-openrouter.md): Move OpenRouter Chat Completions requests to AnyRouter, including provider preferences for ordering, price caps, and fallbacks. - [AnyRouter vs OpenRouter](https://anyrouter.dev/docs/guides/anyrouter-vs-openrouter.md): An honest comparison of AnyRouter and OpenRouter — one-command agent launcher, BYO keys + subscriptions, config that follows you, and failover across your own pool. - [Errors](https://anyrouter.dev/docs/guides/errors.md): HTTP status codes, the error envelope, and recommended retry behavior for every AnyRouter API error. - [Provider Routing](https://anyrouter.dev/docs/guides/provider-routing.md): Route requests across upstream providers. Customize ordering, sorting, fallbacks, performance thresholds, data policies, and pricing budgets per request. - [Model Fallbacks](https://anyrouter.dev/docs/guides/model-fallbacks.md): Configure automatic failover between AI models when providers are down, rate-limited, or return retryable errors. - [Sign in with AnyRouter](https://anyrouter.dev/docs/guides/sign-in-with-anyrouter.md): Let users sign in to your app with their AnyRouter account and run AI requests billed to them — no API keys to collect or store. - [Latency Overhead](https://anyrouter.dev/docs/guides/latency-overhead.md): How much latency AnyRouter adds compared to calling the upstream provider directly — and when AnyRouter is actually faster. - [Vercel AI SDK](https://anyrouter.dev/docs/guides/vercel-ai-sdk.md): Configure the Vercel AI SDK's OpenAI provider to stream and generate text through AnyRouter. - [LangChain](https://anyrouter.dev/docs/guides/langchain.md): Point LangChain's OpenAI integrations at AnyRouter to reach every model through one endpoint. - [LlamaIndex](https://anyrouter.dev/docs/guides/llamaindex.md): Point LlamaIndex's OpenAI LLM class at AnyRouter to power RAG, search, and agent loops with any model. - [LiteLLM](https://anyrouter.dev/docs/guides/litellm.md): Route LiteLLM client calls and proxy models through AnyRouter as a custom OpenAI-compatible provider. - [curl](https://anyrouter.dev/docs/guides/curl.md): Call AnyRouter's OpenAI-compatible API straight from the terminal with curl — for quick tests, scripts, and CI. ## Scenario Examples - [How to Unify AI Subscriptions with AnyRouter](https://anyrouter.dev/docs/scenario-examples/unify-ai-subscriptions.md): Bring Z-AI, Kimi, OpenAI, Anthropic, and other provider accounts into one AnyRouter preset, then launch Claude Code through one CLI wrapper. - [Cut LLM Costs with Automatic Provider Fallback](https://anyrouter.dev/docs/scenario-examples/cut-costs-provider-fallback.md): Route one model id across multiple upstreams so AnyRouter picks the cheapest healthy provider and falls back automatically when one is down. - [Add BYOK to an Existing App](https://anyrouter.dev/docs/scenario-examples/add-byok-to-existing-app.md): Attach your own provider keys to AnyRouter so your existing integration bills against your provider accounts at list price, with one base URL change. - [Run Claude Code Against AnyRouter](https://anyrouter.dev/docs/scenario-examples/run-claude-code-on-anyrouter.md): Point Claude Code at AnyRouter so every coding session is billed once, logged, and free to use any Messages-compatible model in the catalog. - [Run OpenCode Against AnyRouter](https://anyrouter.dev/docs/scenario-examples/run-opencode-on-anyrouter.md): Point OpenCode at AnyRouter so every coding session is billed once, logged, and free to use any Chat Completions model in the catalog. - [A/B Compare Models in the Playground](https://anyrouter.dev/docs/scenario-examples/ab-compare-models-playground.md): Send the same prompt to several models from one AnyRouter key and compare answers, latency, and cost side by side before you commit to one. - [Build an Agentic Coding Loop with GLM](https://anyrouter.dev/docs/scenario-examples/agentic-coding-loop-with-glm.md): Wire an AI SDK tool-calling loop to a GLM coding model through AnyRouter, with streaming, multi-step tool use, and an optional BYOK Z-AI key. ## Features - [Skills & Knowledge Hub](https://anyrouter.dev/docs/hub.md): One source of truth for your AI agent's skills, prompts, knowledge, and plugins — managed in the dashboard and synced to every machine and agent with one command. - [Dashboard Overview](https://anyrouter.dev/docs/features/dashboard-overview.md): Check whether anything needs you, scan requests/errors/spend, and open the last five requests from the AnyRouter dashboard home. - [Usage Explorer](https://anyrouter.dev/docs/features/usage-explorer.md): Build cost, token, and request charts grouped by model, key, or time. Filter by date range, export, and read percentile latency. - [Request Logs](https://anyrouter.dev/docs/features/request-logs.md): Inspect individual chat/completion requests — latency breakdown, tokens, cost, upstream provider, and full body when privacy permits. - [Managing API Keys](https://anyrouter.dev/docs/features/api-keys.md): Create, rotate, scope, and rate-limit AnyRouter API keys from the dashboard. Track usage per key and revoke compromised keys instantly. - [Prompt Caching](https://anyrouter.dev/docs/features/caching.md): Cache long system prompts and reusable context across requests to cut cost and latency on conversational, RAG, and agent workloads. - [Pricing & Plans](https://anyrouter.dev/docs/features/pricing.md): AnyRouter's Free, Go, Pro, Pro+, and Max plans, how included credits and pay-as-you-go top-ups fit together, and where each billing surface lives in the dashboard. - [Bring Your Own Key (BYOK)](https://anyrouter.dev/docs/features/byok.md): Attach your own upstream API keys so AnyRouter routes requests through your provider accounts at list price, with no AnyRouter markup. - [Credits & Billing](https://anyrouter.dev/docs/features/credits.md): How AnyRouter credits work — the two credit buckets, how request cost is calculated, plan monthly credits, top-ups, and reading your balance from the API. - [Response Caching](https://anyrouter.dev/docs/features/response-caching.md): Cache identical AI Gateway responses so repeat requests return instantly at zero upstream cost — automatic for deterministic calls, and controllable per request. - [BYOK Provider Setup Guide](https://anyrouter.dev/docs/features/byok-providers.md): Bring your own API keys for every supported upstream provider — pick a provider for step-by-step key setup, then add it under Dashboard → BYOK. - [Share a Key to the Shared Pool](https://anyrouter.dev/docs/features/shared-pool.md): Donate one of your provider keys to the community shared pool, earn up to 8% of the token cost back as credits, and withdraw anytime — a step-by-step guide. - [Models Catalog](https://anyrouter.dev/docs/features/models-catalog.md): Browse models you can call in your workspace, with pricing, context limits, capabilities, and active-use signals. Show all models lists the full catalog. - [Tool Use](https://anyrouter.dev/docs/features/tool-use.md): Define tools, let the model call them, and feed results back. Build agents, function-calling workflows, and structured outputs across every model. - [Free Tier](https://anyrouter.dev/docs/features/free-tier.md): Call a curated set of free models through anyrouter/free — no BYOK setup, no credit deduction. 10 requests/day on Free, 1000/day on paid plans. - [Presets](https://anyrouter.dev/docs/features/presets.md): Create reusable configuration bundles with default models, system prompts, and sampling parameters. Reference them from API requests with @preset syntax. - [Free-tier Aggregation](https://anyrouter.dev/docs/features/free-tier-aggregation.md): Combine multiple providers' free API tiers behind one endpoint, with smart key balancing, automatic quota detection, and an opt-in paid fallback. - [App Attribution](https://anyrouter.dev/docs/features/app-attribution.md): Attribute your API usage to your app with HTTP-Referer and X-AnyRouter headers and appear in public rankings and analytics. - [Privacy & Logging Controls](https://anyrouter.dev/docs/features/privacy-controls.md): Control what AnyRouter retains — request body capture, PII redaction, training opt-out, blocked providers, and data residency. - [Smart Routing](https://anyrouter.dev/docs/features/routing.md): How AnyRouter picks an upstream provider for each request — priority order, automatic failover, model aliases, and explicit override controls. - [How AnyRouter Chooses a Credential](https://anyrouter.dev/docs/features/credential-selection.md): The order AnyRouter checks your own provider keys, the shared pool, and AnyRouter credits — and what happens when a key is rate limited or fails. - [AnyRouter Agent](https://anyrouter.dev/docs/features/anyrouter-agent.md): Free on-site support copilot on anyrouter.dev — ask docs, models, and (after you opt in) your plan and keys without leaving the page. - [Organizations & Workspaces](https://anyrouter.dev/docs/features/organizations.md): Invite teammates, set roles, switch between workspaces, and isolate billing per organization. - [Account Settings](https://anyrouter.dev/docs/features/account-settings.md): Manage your AnyRouter profile, email addresses, authentication methods, and connected devices. - [Local Relay — Serve Models From Your Own Machine](https://anyrouter.dev/docs/features/local-relay.md): Route requests to a model running on your own computer (Apple Foundation Models, Ollama, LM Studio) through your AnyRouter API key, and optionally donate idle capacity to the shared pool for credits. - [Rate Limits](https://anyrouter.dev/docs/features/rate-limits.md): AnyRouter's per-IP and per-key rate limits, how tiers are picked, what 429 vs 403 mean, and how to handle them in your client. - [AI/ML API (BYOK)](https://anyrouter.dev/docs/features/byok-providers/aimlapi.md): How to create an API key for AI/ML API and add it to AnyRouter via Bring Your Own Key. - [AI21 (BYOK)](https://anyrouter.dev/docs/features/byok-providers/ai21.md): How to create an API key for AI21 and add it to AnyRouter via Bring Your Own Key. - [AIHubMix (BYOK)](https://anyrouter.dev/docs/features/byok-providers/aihubmix.md): How to create an API key for AIHubMix and add it to AnyRouter via Bring Your Own Key. - [AionLabs (BYOK)](https://anyrouter.dev/docs/features/byok-providers/aionlabs.md): How to create an API key for AionLabs and add it to AnyRouter via Bring Your Own Key. - [AkashML (BYOK)](https://anyrouter.dev/docs/features/byok-providers/akash.md): How to create an API key for AkashML and add it to AnyRouter via Bring Your Own Key. - [Alibaba Cloud Int. (BYOK)](https://anyrouter.dev/docs/features/byok-providers/alibaba-cloud.md): How to create an API key for Alibaba Cloud Int. and add it to AnyRouter via Bring Your Own Key. - [Amazon Bedrock (BYOK)](https://anyrouter.dev/docs/features/byok-providers/amazon-bedrock.md): How to create an API key for Amazon Bedrock and add it to AnyRouter via Bring Your Own Key. - [Anthropic (BYOK)](https://anyrouter.dev/docs/features/byok-providers/anthropic.md): How to create an API key for Anthropic and add it to AnyRouter via Bring Your Own Key. - [Antigravity (Google) (BYOK)](https://anyrouter.dev/docs/features/byok-providers/antigravity.md): How to create an API key for Antigravity (Google) and add it to AnyRouter via Bring Your Own Key. - [Arcee AI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/arcee.md): How to create an API key for Arcee AI and add it to AnyRouter via Bring Your Own Key. - [AutoJev (BYOK)](https://anyrouter.dev/docs/features/byok-providers/autojev.md): How to create an API key for AutoJev and add it to AnyRouter via Bring Your Own Key. - [Azure (BYOK)](https://anyrouter.dev/docs/features/byok-providers/azure.md): How to create an API key for Azure and add it to AnyRouter via Bring Your Own Key. - [Baseten (BYOK)](https://anyrouter.dev/docs/features/byok-providers/baseten.md): How to create an API key for Baseten and add it to AnyRouter via Bring Your Own Key. - [Blackbox AI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/blackbox.md): How to create an API key for Blackbox AI and add it to AnyRouter via Bring Your Own Key. - [Cerebras (BYOK)](https://anyrouter.dev/docs/features/byok-providers/cerebras.md): How to create an API key for Cerebras and add it to AnyRouter via Bring Your Own Key. - [Chutes (BYOK)](https://anyrouter.dev/docs/features/byok-providers/chutes.md): How to create an API key for Chutes and add it to AnyRouter via Bring Your Own Key. - [Cirrascale (BYOK)](https://anyrouter.dev/docs/features/byok-providers/cirrascale.md): How to create an API key for Cirrascale and add it to AnyRouter via Bring Your Own Key. - [Clarifai (BYOK)](https://anyrouter.dev/docs/features/byok-providers/clarifai.md): How to create an API key for Clarifai and add it to AnyRouter via Bring Your Own Key. - [Cline (BYOK)](https://anyrouter.dev/docs/features/byok-providers/cline.md): How to create an API key for Cline and add it to AnyRouter via Bring Your Own Key. - [Cloudflare (BYOK)](https://anyrouter.dev/docs/features/byok-providers/cloudflare.md): How to create an API key for Cloudflare and add it to AnyRouter via Bring Your Own Key. - [Cohere (BYOK)](https://anyrouter.dev/docs/features/byok-providers/cohere.md): How to create an API key for Cohere and add it to AnyRouter via Bring Your Own Key. - [CommandCode (BYOK)](https://anyrouter.dev/docs/features/byok-providers/commandcode.md): How to create an API key for CommandCode and add it to AnyRouter via Bring Your Own Key. - [Crusoe (BYOK)](https://anyrouter.dev/docs/features/byok-providers/crusoe.md): How to create an API key for Crusoe and add it to AnyRouter via Bring Your Own Key. - [DeepInfra (BYOK)](https://anyrouter.dev/docs/features/byok-providers/deepinfra.md): How to create an API key for DeepInfra and add it to AnyRouter via Bring Your Own Key. - [DeepSeek (BYOK)](https://anyrouter.dev/docs/features/byok-providers/deepseek.md): How to create an API key for DeepSeek and add it to AnyRouter via Bring Your Own Key. - [Experiential (BYOK)](https://anyrouter.dev/docs/features/byok-providers/experiential.md): How to create an API key for Experiential and add it to AnyRouter via Bring Your Own Key. - [Fastino (BYOK)](https://anyrouter.dev/docs/features/byok-providers/fastino.md): How to create an API key for Fastino and add it to AnyRouter via Bring Your Own Key. - [Featherless (BYOK)](https://anyrouter.dev/docs/features/byok-providers/featherless.md): How to create an API key for Featherless and add it to AnyRouter via Bring Your Own Key. - [Fireworks (BYOK)](https://anyrouter.dev/docs/features/byok-providers/fireworks.md): How to create an API key for Fireworks and add it to AnyRouter via Bring Your Own Key. - [Friendli (BYOK)](https://anyrouter.dev/docs/features/byok-providers/friendli.md): How to create an API key for Friendli and add it to AnyRouter via Bring Your Own Key. - [GMICloud (BYOK)](https://anyrouter.dev/docs/features/byok-providers/gmicloud.md): How to create an API key for GMICloud and add it to AnyRouter via Bring Your Own Key. - [Google AI Studio (BYOK)](https://anyrouter.dev/docs/features/byok-providers/google-ai-studio.md): How to create an API key for Google AI Studio and add it to AnyRouter via Bring Your Own Key. - [Google Vertex (BYOK)](https://anyrouter.dev/docs/features/byok-providers/google-vertex.md): How to create an API key for Google Vertex and add it to AnyRouter via Bring Your Own Key. - [Groq (BYOK)](https://anyrouter.dev/docs/features/byok-providers/groq.md): How to create an API key for Groq and add it to AnyRouter via Bring Your Own Key. - [Hugging Face (BYOK)](https://anyrouter.dev/docs/features/byok-providers/huggingface.md): How to create an API key for Hugging Face and add it to AnyRouter via Bring Your Own Key. - [Inception (BYOK)](https://anyrouter.dev/docs/features/byok-providers/inception.md): How to create an API key for Inception and add it to AnyRouter via Bring Your Own Key. - [Inceptron (BYOK)](https://anyrouter.dev/docs/features/byok-providers/inceptron.md): How to create an API key for Inceptron and add it to AnyRouter via Bring Your Own Key. - [Infermatic (BYOK)](https://anyrouter.dev/docs/features/byok-providers/infermatic.md): How to create an API key for Infermatic and add it to AnyRouter via Bring Your Own Key. - [Inflection (BYOK)](https://anyrouter.dev/docs/features/byok-providers/inflection.md): How to create an API key for Inflection and add it to AnyRouter via Bring Your Own Key. - [io.net (BYOK)](https://anyrouter.dev/docs/features/byok-providers/io-net.md): How to create an API key for io.net and add it to AnyRouter via Bring Your Own Key. - [Liquid (BYOK)](https://anyrouter.dev/docs/features/byok-providers/liquid.md): How to create an API key for Liquid and add it to AnyRouter via Bring Your Own Key. - [LLM Gateway (BYOK)](https://anyrouter.dev/docs/features/byok-providers/llmgateway.md): How to create an API key for LLM Gateway and add it to AnyRouter via Bring Your Own Key. - [LongCat (BYOK)](https://anyrouter.dev/docs/features/byok-providers/longcat.md): How to create an API key for LongCat and add it to AnyRouter via Bring Your Own Key. - [Mancer (BYOK)](https://anyrouter.dev/docs/features/byok-providers/mancer.md): How to create an API key for Mancer and add it to AnyRouter via Bring Your Own Key. - [MiniMax (BYOK)](https://anyrouter.dev/docs/features/byok-providers/minimax.md): How to create an API key for MiniMax and add it to AnyRouter via Bring Your Own Key. - [Mistral (BYOK)](https://anyrouter.dev/docs/features/byok-providers/mistral.md): How to create an API key for Mistral and add it to AnyRouter via Bring Your Own Key. - [Moonshot AI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/moonshot.md): How to create an API key for Moonshot AI and add it to AnyRouter via Bring Your Own Key. - [Morph (BYOK)](https://anyrouter.dev/docs/features/byok-providers/morph.md): How to create an API key for Morph and add it to AnyRouter via Bring Your Own Key. - [MuleRouter (BYOK)](https://anyrouter.dev/docs/features/byok-providers/mulerouter.md): How to create an API key for MuleRouter and add it to AnyRouter via Bring Your Own Key. - [Nebius Token Factory (BYOK)](https://anyrouter.dev/docs/features/byok-providers/nebius.md): How to create an API key for Nebius Token Factory and add it to AnyRouter via Bring Your Own Key. - [NextBit (BYOK)](https://anyrouter.dev/docs/features/byok-providers/nextbit.md): How to create an API key for NextBit and add it to AnyRouter via Bring Your Own Key. - [Nous Research (BYOK)](https://anyrouter.dev/docs/features/byok-providers/nousresearch.md): How to create an API key for Nous Research and add it to AnyRouter via Bring Your Own Key. - [NovitaAI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/novita.md): How to create an API key for NovitaAI and add it to AnyRouter via Bring Your Own Key. - [NVIDIA NIM (BYOK)](https://anyrouter.dev/docs/features/byok-providers/nvidia.md): How to create an API key for NVIDIA NIM and add it to AnyRouter via Bring Your Own Key. - [Ollama Cloud (BYOK)](https://anyrouter.dev/docs/features/byok-providers/ollama.md): How to create an API key for Ollama Cloud and add it to AnyRouter via Bring Your Own Key. - [OpenAI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/openai.md): How to create an API key for OpenAI and add it to AnyRouter via Bring Your Own Key. - [OpenCode Zen (BYOK)](https://anyrouter.dev/docs/features/byok-providers/opencode-zen.md): How to create an API key for OpenCode Zen and add it to AnyRouter via Bring Your Own Key. - [OpenCode Zen Go (BYOK)](https://anyrouter.dev/docs/features/byok-providers/opencode-go.md): How to create an API key for OpenCode Zen Go and add it to AnyRouter via Bring Your Own Key. - [OpenInference (BYOK)](https://anyrouter.dev/docs/features/byok-providers/openinference.md): How to create an API key for OpenInference and add it to AnyRouter via Bring Your Own Key. - [OpenRouter (BYOK)](https://anyrouter.dev/docs/features/byok-providers/openrouter.md): How to create an API key for OpenRouter and add it to AnyRouter via Bring Your Own Key. - [OrcaRouter (BYOK)](https://anyrouter.dev/docs/features/byok-providers/orcarouter.md): How to create an API key for OrcaRouter and add it to AnyRouter via Bring Your Own Key. - [OVHcloud (BYOK)](https://anyrouter.dev/docs/features/byok-providers/ovhcloud.md): How to create an API key for OVHcloud and add it to AnyRouter via Bring Your Own Key. - [Parasail (BYOK)](https://anyrouter.dev/docs/features/byok-providers/parasail.md): How to create an API key for Parasail and add it to AnyRouter via Bring Your Own Key. - [Perplexity (BYOK)](https://anyrouter.dev/docs/features/byok-providers/perplexity.md): How to create an API key for Perplexity and add it to AnyRouter via Bring Your Own Key. - [Phala (BYOK)](https://anyrouter.dev/docs/features/byok-providers/phala.md): How to create an API key for Phala and add it to AnyRouter via Bring Your Own Key. - [Poolside (BYOK)](https://anyrouter.dev/docs/features/byok-providers/poolside.md): How to create an API key for Poolside and add it to AnyRouter via Bring Your Own Key. - [Qwen (Alibaba) (BYOK)](https://anyrouter.dev/docs/features/byok-providers/qwen.md): How to create an API key for Qwen (Alibaba) and add it to AnyRouter via Bring Your Own Key. - [QwenCloud (BYOK)](https://anyrouter.dev/docs/features/byok-providers/qwencloud.md): How to create an API key for QwenCloud and add it to AnyRouter via Bring Your Own Key. - [Reka AI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/reka.md): How to create an API key for Reka AI and add it to AnyRouter via Bring Your Own Key. - [Relace (BYOK)](https://anyrouter.dev/docs/features/byok-providers/relace.md): How to create an API key for Relace and add it to AnyRouter via Bring Your Own Key. - [Requesty (BYOK)](https://anyrouter.dev/docs/features/byok-providers/requesty.md): How to create an API key for Requesty and add it to AnyRouter via Bring Your Own Key. - [Respan (BYOK)](https://anyrouter.dev/docs/features/byok-providers/respan.md): How to create an API key for Respan and add it to AnyRouter via Bring Your Own Key. - [Sakana AI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/sakana.md): How to create an API key for Sakana AI and add it to AnyRouter via Bring Your Own Key. - [SambaNova (BYOK)](https://anyrouter.dev/docs/features/byok-providers/sambanova.md): How to create an API key for SambaNova and add it to AnyRouter via Bring Your Own Key. - [SiliconFlow (BYOK)](https://anyrouter.dev/docs/features/byok-providers/siliconflow.md): How to create an API key for SiliconFlow and add it to AnyRouter via Bring Your Own Key. - [StepFun (BYOK)](https://anyrouter.dev/docs/features/byok-providers/stepfun.md): How to create an API key for StepFun and add it to AnyRouter via Bring Your Own Key. - [StepFun Step Plan (BYOK)](https://anyrouter.dev/docs/features/byok-providers/stepplan.md): How to create an API key for StepFun Step Plan and add it to AnyRouter via Bring Your Own Key. - [Switchpoint (BYOK)](https://anyrouter.dev/docs/features/byok-providers/switchpoint.md): How to create an API key for Switchpoint and add it to AnyRouter via Bring Your Own Key. - [Together (BYOK)](https://anyrouter.dev/docs/features/byok-providers/together.md): How to create an API key for Together and add it to AnyRouter via Bring Your Own Key. - [TypeSafe (BYOK)](https://anyrouter.dev/docs/features/byok-providers/typesafe.md): How to create an API key for TypeSafe and add it to AnyRouter via Bring Your Own Key. - [Venice (BYOK)](https://anyrouter.dev/docs/features/byok-providers/venice.md): How to create an API key for Venice and add it to AnyRouter via Bring Your Own Key. - [Vercel AI Gateway (BYOK)](https://anyrouter.dev/docs/features/byok-providers/vercel.md): How to create an API key for Vercel AI Gateway and add it to AnyRouter via Bring Your Own Key. - [Wafer (BYOK)](https://anyrouter.dev/docs/features/byok-providers/wafer.md): How to create an API key for Wafer and add it to AnyRouter via Bring Your Own Key. - [Weights & Biases (BYOK)](https://anyrouter.dev/docs/features/byok-providers/wandb.md): How to create an API key for Weights & Biases and add it to AnyRouter via Bring Your Own Key. - [xAI (BYOK)](https://anyrouter.dev/docs/features/byok-providers/xai.md): How to create an API key for xAI and add it to AnyRouter via Bring Your Own Key. - [Xiaomi (BYOK)](https://anyrouter.dev/docs/features/byok-providers/xiaomi.md): How to create an API key for Xiaomi and add it to AnyRouter via Bring Your Own Key. - [Z.ai (BYOK)](https://anyrouter.dev/docs/features/byok-providers/z-ai.md): How to create an API key for Z.ai and add it to AnyRouter via Bring Your Own Key. - [Z.ai (Coding Plan) (BYOK)](https://anyrouter.dev/docs/features/byok-providers/z-ai-coding.md): How to create an API key for Z.ai (Coding Plan) and add it to AnyRouter via Bring Your Own Key. - [ZenMux (BYOK)](https://anyrouter.dev/docs/features/byok-providers/zenmux.md): How to create an API key for ZenMux and add it to AnyRouter via Bring Your Own Key. ## MCP - [AnyRouter MCP Overview](https://anyrouter.dev/docs/mcp.md): Bring AnyRouter into Claude Desktop, Claude Code, Cursor, OpenCode, and any other MCP-aware client with one URL and OAuth consent. - [MCP Gateway — connect your tools once](https://anyrouter.dev/docs/mcp/gateway.md): Point any MCP client at one URL and get AnyRouter's native tools plus every connected third-party MCP server, with auth managed for you. - [AnyRouter MCP with Claude Desktop](https://anyrouter.dev/docs/mcp/claude-desktop.md): Add the AnyRouter MCP server to Claude Desktop via the built-in Connectors UI, or with a manual mcp-remote bridge. - [AnyRouter MCP with Claude Code](https://anyrouter.dev/docs/mcp/claude-code.md): Add the AnyRouter MCP server to Claude Code (CLI) with one command or by editing .mcp.json. - [AnyRouter MCP with Cursor](https://anyrouter.dev/docs/mcp/cursor.md): Add the AnyRouter MCP server to Cursor via the Settings UI or by editing ~/.cursor/mcp.json. - [AnyRouter MCP with Windsurf](https://anyrouter.dev/docs/mcp/windsurf.md): Add the AnyRouter MCP server to Windsurf via the Cascade Settings UI or by editing ~/.codeium/windsurf/mcp_config.json. - [AnyRouter MCP with Cline](https://anyrouter.dev/docs/mcp/cline.md): Add the AnyRouter MCP server to Cline (VS Code extension) via the MCP Servers panel or cline_mcp_settings.json. - [AnyRouter MCP with GitHub Copilot](https://anyrouter.dev/docs/mcp/github-copilot.md): Add the AnyRouter MCP server to GitHub Copilot Chat in VS Code via .vscode/mcp.json or settings.json. - [AnyRouter MCP with OpenCode](https://anyrouter.dev/docs/mcp/opencode.md): Add the AnyRouter MCP server to OpenCode via a project-local or global opencode.json. - [AnyRouter MCP with other clients](https://anyrouter.dev/docs/mcp/other-clients.md): Connect any MCP-aware client to AnyRouter using the standard remote HTTP transport, OAuth, or a static API key. ## API Reference - [API Overview](https://anyrouter.dev/docs/api-reference/overview.md): Choose the right AnyRouter inference surface — Chat Completions, Messages, Responses, Embeddings — plus catalog and status endpoints. - [Chat Completions API](https://anyrouter.dev/docs/api-reference/chat-completions.md): POST /api/v1/chat/completions — the OpenAI-compatible chat endpoint. Send messages, get a completion, across every model in the catalog. - [Messages API](https://anyrouter.dev/docs/api-reference/messages.md): POST /api/v1/messages — the Anthropic-compatible Messages endpoint. Point any Anthropic SDK or Claude Code at AnyRouter by swapping the base URL. - [Responses API](https://anyrouter.dev/docs/api-reference/responses.md): /api/v1/responses — the OpenAI Responses-compatible lifecycle. Send input, stream or retrieve responses, continue state, and inspect input items. - [Images API](https://anyrouter.dev/docs/api-reference/images.md): Image generation is not supported. AnyRouter is a text and embeddings API. - [OCR API](https://anyrouter.dev/docs/api-reference/ocr.md): POST /api/v1/ocr/extract — extract text from images and documents as Markdown, powered by Cloudflare Workers AI. - [Embeddings API](https://anyrouter.dev/docs/api-reference/embeddings.md): POST /api/v1/embeddings — generate text embeddings for semantic search, clustering, and classification. OpenAI-compatible. - [Decisions API](https://anyrouter.dev/docs/api-reference/systemone.md): POST /api/v1/decisions — typed decisions. Send state and typed questions; get structured answers. Not chat. POST /api/v1/systemone is the same handler. - [Models API](https://anyrouter.dev/docs/api-reference/models.md): GET /api/v1/models — list models you can call, plus pricing, context windows, capabilities, and live provider routing. Pass all=1 for the full catalog. - [Providers API](https://anyrouter.dev/docs/api-reference/providers.md): List the upstream backends AnyRouter can dispatch requests to. - [Health API](https://anyrouter.dev/docs/api-reference/health.md): GET /api/v1/health — live snapshot with status, checked_at, and per-component health. - [Management API Keys](https://anyrouter.dev/docs/api-reference/management-keys.md): Programmatic credentials for managing your AnyRouter account — keys, presets, BYOK, and credits. - [API Keys](https://anyrouter.dev/docs/api-reference/keys.md): Inspect, create, update, and delete AnyRouter LLM API keys. - [Presets API](https://anyrouter.dev/docs/api-reference/presets.md): Create, list, update, and delete reusable preset configurations. - [OAuth](https://anyrouter.dev/docs/api-reference/oauth.md): Mint a scoped API key from an existing key (PKCE), or authorize a browser-less device. For "let my users sign in with their AnyRouter account," see the Sign in with AnyRouter guide instead. - [Credits API](https://anyrouter.dev/docs/api-reference/credits.md): Check the remaining credit balance for your AnyRouter workspace. - [MCP API Reference](https://anyrouter.dev/docs/api-reference/mcp.md): JSON-RPC tool catalog, scopes, error shapes, and manual authentication for the AnyRouter MCP server. - [Network Stats API](https://anyrouter.dev/docs/api-reference/network-stats.md): Public aggregate network analytics — total tokens processed, top models, and activity trends. ## Blog - [anyr decision puts structured decisions in your terminal](https://anyrouter.dev/blog/anyr-decision-cli): Run 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. - [anyr decision：在终端运行结构化决策](https://anyrouter.dev/blog/zh/anyr-decision-cli): 用一条原生 CLI 命令运行 TypeSafe Jev、Fastino GLiNER2.5-Decide 或 anyrouter/decision，不再把决策模型塞进聊天代理。 - [anyr decision đưa quyết định có cấu trúc vào terminal](https://anyrouter.dev/blog/vi/anyr-decision-cli): Chạy TypeSafe Jev, Fastino GLiNER2.5-Decide hoặc anyrouter/decision bằng một lệnh CLI native, không ép mô hình quyết định vào trợ lý chat. - [Jev Decisions is now on its model page](https://anyrouter.dev/blog/jev-decisions): Jev turns application state and typed questions into structured answers with probabilities. Try the new model-page demo, the full Decisions app, or the playground. - [Jev Decisions 已上线模型页](https://anyrouter.dev/blog/zh/jev-decisions): Jev 把应用状态和类型化问题转换为带概率的结构化答案。现在可以在模型页、完整 Decisions 应用和 playground 里试用。 - [Jev Decisions đã có trên trang model](https://anyrouter.dev/blog/vi/jev-decisions): Jev biến trạng thái ứng dụng và câu hỏi có kiểu thành câu trả lời có cấu trúc kèm xác suất. Hãy thử trên trang model, app Decisions hoặc playground. - [Space Bunny Alpha is free on AnyRouter](https://anyrouter.dev/blog/space-bunny-alpha): The anonymous stealth preview is live with a 1M-token context, adjustable reasoning, multimodal input, and $0/$0 catalog routes while it is cloaked. - [Space Bunny Alpha 已在 AnyRouter 免费提供](https://anyrouter.dev/blog/zh/space-bunny-alpha): 这个匿名 stealth 预览模型已上线，拥有 1M token 上下文、可调 reasoning、多模态输入，以及 cloaked 期间 $0/$0 的目录路由。 - [Space Bunny Alpha đã miễn phí trên AnyRouter](https://anyrouter.dev/blog/vi/space-bunny-alpha): Bản preview stealth ẩn danh đã ra mắt với context 1M token, reasoning có thể điều chỉnh, đầu vào đa phương tiện và route catalog $0/$0 khi còn cloaked. - [A shared key pool, and a free-token pool on the other side](https://anyrouter.dev/blog/intro): AnyRouter 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. - [共享 key 池，另一头是给用户的免费 token 池](https://anyrouter.dev/blog/zh/intro): AnyRouter 一开始只是「一个 URL 打到很多模型」。真正要紧的是池子：有人把闲置的供应商 key 捐进来，网关在这些 key 之间调度，其他人不用自己去找一把还能用的 key，就能从免费 token 池里取用量。 - [Một pool key dùng chung, và một pool token miễn phí phía bên kia](https://anyrouter.dev/blog/vi/intro): AnyRouter bắt đầu như một URL đứng trước nhiều model. Phần quan trọng thật sự là cái pool: người ta góp key nhà cung cấp đang dư, gateway điều phối quanh chúng, và người khác lấy token từ pool miễn phí thay vì tự đi tìm một key còn chạy được. - [AnyRouter vs OpenRouter: a practical comparison](https://anyrouter.dev/blog/anyrouter-vs-openrouter): Both route one API across many models. AnyRouter is $0-markup on your own keys, runs at the Cloudflare edge, and a $2/mo Go plan ($4 credits) unlocks free models — Free has no monthly credits. Here is the verifiable difference. - [AnyRouter 对 OpenRouter：实用对比](https://anyrouter.dev/blog/zh/anyrouter-vs-openrouter): 两边都是一个 API 打到很多模型。AnyRouter 在你自己的 key 上 $0 加价，跑在 Cloudflare 边缘，每月 $2 的 Go（$4 额度）解锁免费模型——Free 没有月度额度。下面是能核对的差别。 - [AnyRouter và OpenRouter: so sánh thực tế](https://anyrouter.dev/blog/vi/anyrouter-vs-openrouter): Cả hai route một API qua nhiều model. AnyRouter markup $0 trên key của bạn, chạy ở cạnh Cloudflare, và gói Go $2/tháng ($4 credit) mở model miễn phí — Free không có credit tháng. Đây là khác biệt kiểm chứng được. - [在 anyrouter.dev 上跑 Claude Code（BYOK、捐 key、anyr claude）](https://anyrouter.dev/blog/zh/anyrouter-zhongzhuan): 官方站是 anyrouter.dev。文档 docs.anyrouter.dev，控制台 dash.anyrouter.dev。Free 没有每月赠送额度。Go 是 $2/月（Polar 卡上扣 $2.63）→ $4 额度。curl setup.sh，然后 anyr claude。ANTHROPIC_BASE_URL=https://anyrouter.dev/api。没有支付宝，也没有微信。 - [Claude Code on anyrouter.dev](https://anyrouter.dev/blog/claude-code-anyrouter-dev): Claude 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. - [在 anyrouter.dev 上用 Claude Code](https://anyrouter.dev/blog/zh/claude-code-anyrouter-dev): Claude Code 走 anyrouter.dev。setup.sh 然后 anyr claude。ANTHROPIC_BASE_URL=https://anyrouter.dev/api。Free 没有月度额度；Go 是 $2/月（实收 $2.63）→ $4。 - [Claude Code trên anyrouter.dev](https://anyrouter.dev/blog/vi/claude-code-anyrouter-dev): Claude Code trên anyrouter.dev. setup.sh rồi anyr claude. ANTHROPIC_BASE_URL=https://anyrouter.dev/api. Free không có credit tháng; Go là $2/tháng (trừ $2.63) → $4. - [Donate a key for Go — no card](https://anyrouter.dev/blog/donate-a-key-for-go): Two 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. - [捐一把 key 换 Go，不用绑卡](https://anyrouter.dev/blog/zh/donate-a-key-for-go): 开通 Go 有两条路：付 $2/月（卡上扣 $2.63，$4 额度），或捐一把可用的 BYOK key（DeepSeek、Z.ai GLM、Moonshot Kimi）。没有支付宝，也没有微信。捐赠分成 5%/8%，每把 key 每个 UTC 日上限 $1——这个 $1 是捐赠上限，不是 Go 价格。 - [Góp một key để lấy Go — không cần thẻ](https://anyrouter.dev/blog/vi/donate-a-key-for-go): Hai cách mở Go: trả $2/tháng (thẻ bị trừ $2.63, $4 credit) hoặc góp một key BYOK đủ điều kiện (DeepSeek, Z.ai GLM, Moonshot Kimi). Không Alipay, không WeChat. Chia cho người góp 5%/8%, trần $1 mỗi key mỗi ngày UTC — $1 đó là trần thưởng, không phải giá Go. - [AnyRouter pricing: Free vs Go (the $1 posts are wrong)](https://anyrouter.dev/blog/anyrouter-pricing-free-vs-go): Older pages still say $1 Go — wrong. Free has no monthly credits; anyrouter/free is 10 req/day. Go is $2/mo ($2.63 charged) → $4. Pro $10 ($11.05) → $20; Pro+ $45 ($47.89) → $100; Max $100 ($105.79) → $300. - [AnyRouter 定价：Free 对 Go（写 $1 Go 的帖子是错的）](https://anyrouter.dev/blog/zh/anyrouter-pricing-free-vs-go): 旧页还写 $1 Go——错。Free 没有月度额度；anyrouter/free 是每天 10 次。Go 是 $2/月（实收 $2.63）→ $4。Pro $10（$11.05）→ $20；Pro+ $45（$47.89）→ $100；Max $100（$105.79）→ $300。 - [Giá AnyRouter: Free và Go (bài viết $1 Go là sai)](https://anyrouter.dev/blog/vi/anyrouter-pricing-free-vs-go): Trang cũ vẫn nói $1 Go — sai. Free không có credit tháng; anyrouter/free là 10 req/ngày. Go là $2/tháng (trừ $2.63) → $4. Pro $10 ($11.05) → $20; Pro+ $45 ($47.89) → $100; Max $100 ($105.79) → $300. - [Ox Alpha is now GLM-5.3-Flash](https://anyrouter.dev/blog/glm-5-3-flash): The 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. - [Ox Alpha 现在叫 GLM-5.3-Flash](https://anyrouter.dev/blog/zh/glm-5-3-flash): Ox Alpha 预览就是 GLM-5.3-Flash：原生多模态、1M 上下文、MIT 许可的 320B-A18B。同一套 AnyRouter 路由，新目录 id 是 z-ai/glm-5.3-flash。 - [Ox Alpha giờ là GLM-5.3-Flash](https://anyrouter.dev/blog/vi/glm-5-3-flash): Bản xem trước Ox Alpha chính là GLM-5.3-Flash: đa phương tiện gốc, ngữ cảnh 1M, 320B-A18B giấy phép MIT. Cùng route AnyRouter, catalog id mới z-ai/glm-5.3-flash. - [Qwen3.8-27B and DeepSeek V4 Flash, 50% off](https://anyrouter.dev/blog/qwen3-8-27b-50-percent-off): Half off through 1 Sep. Same API, same model ids — just a friendlier bill. - [Qwen3.8-27B 和 DeepSeek V4 Flash，五折](https://anyrouter.dev/blog/zh/qwen3-8-27b-50-percent-off): 五折到 9 月 1 日。同一套 API、同一套 model id——账单更友好。 - [Qwen3.8-27B và DeepSeek V4 Flash, giảm 50%](https://anyrouter.dev/blog/vi/qwen3-8-27b-50-percent-off): Nửa giá đến 1 tháng 9. Cùng API, cùng model id — hóa đơn dễ chịu hơn. - [Use OpenCode with AnyRouter — CLI launcher or opencode.json](https://anyrouter.dev/blog/opencode-anyrouter): Point 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. - [用 AnyRouter 跑 OpenCode — CLI 启动器或 opencode.json](https://anyrouter.dev/blog/zh/opencode-anyrouter): 一条命令把 OpenCode 编程 agent 指到 AnyRouter，或在 opencode.json 里加一个自定义 Chat Completions 供应商。一把 sk-ar- key 打到目录里每个模型，账单和请求日志统一。 - [Dùng OpenCode với AnyRouter — CLI launcher hoặc opencode.json](https://anyrouter.dev/blog/vi/opencode-anyrouter): Chỉ coding agent OpenCode vào AnyRouter bằng một lệnh, hoặc thêm nhà cung cấp Chat Completions tùy chỉnh trong opencode.json. Một key sk-ar- tới mọi model catalog, billing và nhật ký request thống nhất. - [CLI update: multiple accounts, terminal key management, and agents that delegate](https://anyrouter.dev/blog/cli-accounts-and-delegation): The 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. - [CLI 更新：多账号、终端管 key、agent 互相委派](https://anyrouter.dev/blog/zh/cli-accounts-and-delegation): AnyRouter CLI 现在可以并排管理多个账号，不进 dashboard 也能管 API key，用两个模型跑「先计划再实现」流水线，并让 coding agent 互相交活——一跳、一把 key。 - [Cập nhật CLI: nhiều tài khoản, quản lý key trên terminal, và agent ủy thác](https://anyrouter.dev/blog/vi/cli-accounts-and-delegation): CLI AnyRouter giờ giữ vài tài khoản cạnh nhau, quản lý API key không cần dashboard, chạy pipeline lập kế hoạch rồi implement trên hai mô hình, và để coding agent giao việc cho nhau — một hop, một key. - [What is AnyRouter? A plain-English guide to AI model routing](https://anyrouter.dev/blog/what-is-anyrouter): An AI model router lets you call many LLMs through one API. Here's what AnyRouter is, why it exists, and whether it's useful for your next project. - [AnyRouter 是什么？用人话讲 AI 模型路由](https://anyrouter.dev/blog/zh/what-is-anyrouter): AI 模型路由器让你用一个 API 调用很多 LLM。下面讲 AnyRouter 是什么、为什么存在、对你下一个项目有没有用。 - [AnyRouter là gì? Giải thích routing model AI bằng tiếng thường](https://anyrouter.dev/blog/vi/what-is-anyrouter): Router model AI cho phép gọi nhiều LLM qua một API. Đây là AnyRouter là gì, vì sao tồn tại, và có ích cho dự án tiếp theo của bạn không. - [HTTP 429 and 503 errors when calling AI APIs: what they mean and how to fix them](https://anyrouter.dev/blog/anyrouter-429-error-fix): If you've hit a 429 Too Many Requests or 503 Service Unavailable on AnyRouter or another AI gateway, the cause is almost always rate limiting or upstream overload. Here are the practical fixes. - [调用 AI API 时的 HTTP 429 和 503：含义和怎么修](https://anyrouter.dev/blog/zh/anyrouter-429-error-fix): 如果你在 AnyRouter 或其他 AI 网关上碰到 429 Too Many Requests 或 503 Service Unavailable，原因几乎总是限流或上游过载。下面是能落地的修法。 - [Lỗi HTTP 429 và 503 khi gọi AI API: nghĩa là gì và sửa thế nào](https://anyrouter.dev/blog/vi/anyrouter-429-error-fix): Nếu bạn gặp 429 Too Many Requests hoặc 503 Service Unavailable trên AnyRouter hay gateway AI khác, nguyên nhân gần như luôn là rate limit hoặc upstream quá tải. Đây là cách xử lý thực tế. - [How to use AnyRouter with Claude Code (Anthropic's CLI coding tool)](https://anyrouter.dev/blog/anyrouter-claude-code-setup): Point Claude Code at AnyRouter by setting two environment variables. Here's the setup, what changes, and what to do when things go wrong. - [如何把 Claude Code（Anthropic 官方 CLI 编程工具）接到 AnyRouter](https://anyrouter.dev/blog/zh/anyrouter-claude-code-setup): 设两个环境变量，就能把 Claude Code 指到 AnyRouter。下面是配置、会变什么、以及出问题时怎么处理。 - [Cách dùng AnyRouter với Claude Code (CLI coding của Anthropic)](https://anyrouter.dev/blog/vi/anyrouter-claude-code-setup): Chỉ Claude Code vào AnyRouter bằng hai biến môi trường. Đây là cách cài, những gì đổi, và xử lý khi hỏng. - [Nex-N2-Pro: a free AI model and how to access it via API](https://anyrouter.dev/blog/nex-n2-pro-free-ai-model): Nex-N2-Pro is a free chat model listed under nex-agi on OpenRouter and other model aggregators. Here's what to know before you build with it. - [Nex-N2-Pro：一个免费 AI 模型，以及如何用 API 调用它](https://anyrouter.dev/blog/zh/nex-n2-pro-free-ai-model): Nex-N2-Pro 是 nex-agi 名下的免费对话模型，出现在 OpenRouter 和其他聚合器上。动手前先看这些。 - [Nex-N2-Pro: model AI miễn phí và cách gọi qua API](https://anyrouter.dev/blog/vi/nex-n2-pro-free-ai-model): Nex-N2-Pro là model chat miễn phí của nex-agi trên OpenRouter và các aggregator khác. Đây là những gì cần biết trước khi build. - [Using AnyRouter from Linux, WSL, or a headless server](https://anyrouter.dev/blog/anyrouter-linux-do-setup): AnyRouter works from any machine that can make HTTPS requests — Linux servers, WSL, CI pipelines, and remote dev boxes. Here's the setup and the gotchas. - [在 Linux、WSL 或无头服务器上用 AnyRouter](https://anyrouter.dev/blog/zh/anyrouter-linux-do-setup): 只要能发 HTTPS 请求的机器都能用 AnyRouter — Linux 服务器、WSL、CI、远程开发机。下面是配置和坑。 - [Dùng AnyRouter từ Linux, WSL, hoặc máy không màn hình](https://anyrouter.dev/blog/vi/anyrouter-linux-do-setup): AnyRouter chạy trên mọi máy gửi được HTTPS — server Linux, WSL, CI, hộp dev từ xa. Đây là cài đặt và những chỗ dễ vấp. - [AnyRouter API documentation: base URL, model ids, and request format](https://anyrouter.dev/blog/anyrouter-api-docs-primer): The AnyRouter API is OpenAI-compatible. Here's the base URL, model id format, authentication, and a working request example. - [AnyRouter API 文档：base URL、模型 id、请求格式](https://anyrouter.dev/blog/zh/anyrouter-api-docs-primer): AnyRouter API 兼容 OpenAI。这里是 base URL、模型 id 格式、鉴权，以及一条能跑的请求示例。 - [Tài liệu API AnyRouter: base URL, model id, và định dạng request](https://anyrouter.dev/blog/vi/anyrouter-api-docs-primer): API AnyRouter tương thích OpenAI. Đây là base URL, định dạng model id, xác thực, và một request chạy được. - [Bring your CommandCode credential to AnyRouter](https://anyrouter.dev/blog/commandcode-byok): The CLI now reads your local CommandCode auth file and uploads it as a BYOK key — one command, no copy-paste. - [把 CommandCode 凭据带到 AnyRouter](https://anyrouter.dev/blog/zh/commandcode-byok): CLI 现在会读本机 CommandCode 鉴权文件并上传成 BYOK key — 一条命令，不用复制粘贴。 - [Mang credential CommandCode sang AnyRouter](https://anyrouter.dev/blog/vi/commandcode-byok): CLI giờ đọc file auth CommandCode trên máy và upload thành BYOK key — một lệnh, không copy-paste. - [Run Claude Code on AnyRouter — wrapper script or CLI](https://anyrouter.dev/blog/claude-code-anyrouter): Route 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. - [在 AnyRouter 上跑 Claude Code — wrapper 脚本或 CLI](https://anyrouter.dev/blog/zh/claude-code-anyrouter): 两条路把 Claude Code 接到 AnyRouter：一个会自己安装的 wrapper，把 Opus、Sonnet、Haiku 都映射到同一条目录模型（用 --model 覆盖）；或 anyr CLI 启动器。一把 key，统一账单，审计日志。 - [Chạy Claude Code trên AnyRouter — wrapper hoặc CLI](https://anyrouter.dev/blog/vi/claude-code-anyrouter): Route Claude Code qua AnyRouter theo hai cách: wrapper tự cài và map Opus, Sonnet, Haiku vào một model catalog (ghi đè bằng --model), hoặc launcher anyr CLI. Một key, billing thống nhất, nhật ký. - [Bring your Antigravity credential to AnyRouter](https://anyrouter.dev/blog/antigravity-byok): A 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. - [把 Antigravity 凭据带到 AnyRouter](https://anyrouter.dev/blog/zh/antigravity-byok): 一个 CLI：找到本机 Antigravity 凭据，原样给你看，再上传成 BYOK key — 捐进池是另一次、显式的选择。 - [Mang credential Antigravity sang AnyRouter](https://anyrouter.dev/blog/vi/antigravity-byok): CLI tìm credential Antigravity trên máy, hiện đúng những gì tìm thấy, rồi upload thành BYOK key — góp pool là lựa chọn riêng, tường minh. - [Sign in with AnyRouter: let users bring their own LLM account](https://anyrouter.dev/blog/sign-in-with-anyrouter): If 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. - [Sign in with AnyRouter：让用户带上自己的 LLM 账户](https://anyrouter.dev/blog/zh/sign-in-with-anyrouter): 如果应用要跑 LLM API，你只有两个糟糕选项：自己出 key、吃下每个用户的推理账单，或让每人粘贴一把裸的供应商 key。"Sign in with AnyRouter" 是第三条路——用户用自己的 AnyRouter 账户登录，用他们自己的余额跑推理。你拿到一把临时、仅推理、按用户隔离的 key，从不经手模型账单。 - [Sign in with AnyRouter: để người dùng mang tài khoản LLM của họ](https://anyrouter.dev/blog/vi/sign-in-with-anyrouter): Nếu app cần LLM API để chạy, bạn có hai lựa chọn tệ: tự ship key rồi gánh hóa đơn inference của mọi user, hoặc bắt từng người dán key nhà cung cấp thô. "Sign in with AnyRouter" là lựa chọn thứ ba — họ đăng nhập bằng tài khoản AnyRouter, số dư của họ nuôi inference. Bạn nhận key tạm, chỉ inference, theo từng user, và không đụng billing model. - [Run the Claude Agent SDK on any model](https://anyrouter.dev/blog/claude-agent-sdk-any-model): The 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. - [在任意模型上跑 Claude Agent SDK](https://anyrouter.dev/blog/zh/claude-agent-sdk-any-model): Claude Agent SDK 读 ANTHROPIC_BASE_URL 和 ANTHROPIC_API_KEY，和 Claude Code 用的是同一对变量。把它们指到 AnyRouter，目录里每个模型都能经 Anthropic /messages 方言给 query() 用 — TypeScript 或 Python。 - [Chạy Claude Agent SDK trên bất kỳ model nào](https://anyrouter.dev/blog/vi/claude-agent-sdk-any-model): Claude Agent SDK đọc ANTHROPIC_BASE_URL và ANTHROPIC_API_KEY, cùng hai biến Claude Code dùng. Chỉ chúng vào AnyRouter thì mọi model catalog sẵn cho query() sau dialect Anthropic /messages — TypeScript hoặc Python. - [Use AnyRouter with the Vercel AI SDK](https://anyrouter.dev/blog/ai-sdk-anyrouter): @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. - [用 Vercel AI SDK 接 AnyRouter](https://anyrouter.dev/blog/zh/ai-sdk-anyrouter): @anyr/ai-sdk-provider 把 AnyRouter 网关包成标准 Vercel AI SDK provider。调用 createAnyRouter()，传入 provider/model id，generateText、streamText、generateObject 不用改 — 换模型只改一个字符串。 - [Dùng AnyRouter với Vercel AI SDK](https://anyrouter.dev/blog/vi/ai-sdk-anyrouter): @anyr/ai-sdk-provider bọc gateway AnyRouter thành provider Vercel AI SDK chuẩn. Gọi createAnyRouter(), truyền provider/model id, generateText, streamText, và generateObject chạy không đổi — đổi model là sửa một chuỗi. - [Get a free NVIDIA API key and route it through one URL](https://anyrouter.dev/blog/nvidia-free-key-setup): NVIDIA 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. - [领一把免费 NVIDIA API key，再用一个 URL 转发](https://anyrouter.dev/blog/zh/nvidia-free-key-setup): NVIDIA 发免费 API key，带额度，不用绑卡。把它作为 BYOK 接到 AnyRouter，NVIDIA 托管的模型都走同一个兼容 OpenAI 的端点——加价 $0。下面是大约五分钟的流程。 - [Lấy NVIDIA API key miễn phí rồi route qua một URL](https://anyrouter.dev/blog/vi/nvidia-free-key-setup): NVIDIA phát API key miễn phí kèm credit, không cần thẻ. Gắn vào AnyRouter như BYOK thì mọi model NVIDIA host chạy qua một endpoint tương thích OpenAI — markup $0. Setup khoảng năm phút. - [Set up a Hermes agent with AnyRouter](https://anyrouter.dev/blog/hermes-agent-anyrouter): Run 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. - [用 AnyRouter 跑 Hermes agent](https://anyrouter.dev/blog/zh/hermes-agent-anyrouter): 大约三分钟把 Nous Research 的 Hermes 3 405B 当 agent 跑起来：拿免费 Hugging Face token，接成 BYOK，开一把 AnyRouter key，把兼容 OpenAI 的客户端指到一个 URL。不加价；闲置配额捐出去还能拿回 8%。 - [Chạy Hermes agent với AnyRouter](https://anyrouter.dev/blog/vi/hermes-agent-anyrouter): Chạy Hermes 3 405B của Nous Research như agent trong khoảng ba phút: lấy Hugging Face token miễn phí, gắn BYOK, mint key AnyRouter, chỉ client tương thích OpenAI vào một URL. Không markup; góp quota nhàn nhận lại 8%. - [Point Claude Code at a custom base URL](https://anyrouter.dev/blog/claude-code-through-one-gateway): Claude 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. - [把 Claude Code 指到自定义 base URL](https://anyrouter.dev/blog/zh/claude-code-through-one-gateway): Claude Code 读 ANTHROPIC_BASE_URL 和 ANTHROPIC_API_KEY，指到 AnyRouter 只要两个环境变量——不用插件、不用 fork。同一把 key 后面是整份目录，供应商限流时自动切换，审计日志和 Codex、Cursor 及其他 agent 共用。 - [Chỉ Claude Code vào custom base URL](https://anyrouter.dev/blog/vi/claude-code-through-one-gateway): Claude Code đọc ANTHROPIC_BASE_URL và ANTHROPIC_API_KEY, nên chỉ vào AnyRouter chỉ cần hai biến môi trường — không plugin, không fork. Cùng một key phía sau là cả catalog, failover khi nhà cung cấp bị rate-limit, và một audit log chung với Codex, Cursor và mọi agent khác. - [Use the OpenAI SDK with any model](https://anyrouter.dev/blog/openai-sdk-any-model): The 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. - [用 OpenAI SDK 打任意模型](https://anyrouter.dev/blog/zh/openai-sdk-any-model): 官方 openai 包（Python 和 TypeScript）不必只打 OpenAI 模型。覆盖 base_url 和 api_key，其余调用不变，用 provider/model 字符串寻址 28+ 家供应商的 170+ 模型——包括 OpenAI 自己的。 - [Dùng OpenAI SDK với mọi model](https://anyrouter.dev/blog/vi/openai-sdk-any-model): Gói openai chính thức cho Python và TypeScript không bắt buộc model OpenAI. Ghi đè base_url và api_key, giữ mọi lời gọi khác, địa chỉ 170+ model trên 28+ nhà cung cấp bằng chuỗi provider/model — kể cả của OpenAI. - [Cheapest LLM API: how to actually shop for cost per token](https://anyrouter.dev/blog/cheapest-llm-api): The 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. - [最便宜的 LLM API：怎么真正按 token 成本比价](https://anyrouter.dev/blog/zh/cheapest-llm-api): 最便宜的 LLM API 不是标价最低的那家——而是上面不加价、免费档能覆盖真实用量、还能用你已经在付的供应商 key 转发。下面讲怎么比成本，而不是比一个标题数字。 - [LLM API rẻ nhất: so chi phí từng token cho đúng](https://anyrouter.dev/blog/vi/cheapest-llm-api): LLM API rẻ nhất không phải cái dán giá thấp nhất — mà là cái không cộng markup, free tier cover được lượng dùng thật, và có đường route trên key nhà cung cấp bạn đã trả. Đây là cách so chi phí, không so số headline. - [Free LLM API access for students and side projects](https://anyrouter.dev/blog/free-llm-api-for-students): You 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. - [给学生和 side project 的免费 LLM API](https://anyrouter.dev/blog/zh/free-llm-api-for-students): 用真模型做东西不必先有公司卡。在不花 credit 的免费档、$2/月（用量涨了再升）以及把你可能已有的供应商免费档 key（例如 Google AI Studio）接进来之间，有一条能在课堂项目或副业还在成形时把花费留在 $0 的路。 - [API LLM miễn phí cho sinh viên và side project](https://anyrouter.dev/blog/vi/free-llm-api-for-students): Bạn không cần thẻ công ty để dựng với mô hình thật. Giữa free tier không tiêu credit, gói $2/tháng nếu vượt, và route trên key free-tier bạn có thể đã có từ nhà như Google AI Studio, có cách bền để ở $0 trong lúc bài lớp hoặc side hustle còn đang định hình. - [MCP servers for AI agents: what they are and how to connect one](https://anyrouter.dev/blog/mcp-servers-for-ai-agents): An 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. - [给 AI agent 用的 MCP 服务器：是什么、怎么连](https://anyrouter.dev/blog/zh/mcp-servers-for-ai-agents): MCP 服务器让 AI agent 经一套标准接口调用工作区工具——key、额度、模型、状态——而不是每个服务手写胶水。MCP 是什么，以及如何把 AnyRouter 托管的 MCP 服务器接到 Claude Desktop、Claude Code、Cursor 或你自己的 agent。 - [MCP server cho AI agent: chúng là gì và cách kết nối một cái](https://anyrouter.dev/blog/vi/mcp-servers-for-ai-agents): MCP server cho AI agent gọi tool của workspace — key, credit, model, trạng thái — trên một giao diện chuẩn thay vì glue code tùy biến mỗi dịch vụ. MCP là gì và cách nối MCP server được quản lý của AnyRouter vào Claude Desktop, Claude Code, Cursor, hoặc agent của bạn. - [Calling providers directly vs. routing through one gateway](https://anyrouter.dev/blog/direct-provider-vs-gateway): Call 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. - [直连供应商 vs. 经一个网关路由](https://anyrouter.dev/blog/zh/direct-provider-vs-gateway): 直接打 OpenAI、Anthropic 和每个其他供应商，你就要为每个供应商管一把 key、一套 SDK、一份审计轨迹。把同样的调用经一个网关走，每样只管一份——代价是多一跳。下面是 auth、SDK、failover、账单、审计日志和切换成本的老实权衡。 - [Gọi nhà cung cấp trực tiếp vs. route qua một gateway](https://anyrouter.dev/blog/vi/direct-provider-vs-gateway): Gọi OpenAI, Anthropic và mọi nhà cung cấp khác trực tiếp thì bạn quản lý một key, một SDK, và một audit trail mỗi nhà. Route cùng những call đó qua một gateway thì bạn quản lý mỗi thứ một cái — đổi lấy một hop thêm. Đây là đánh đổi thẳng thắn về auth, SDK, failover, billing, audit log, và chi phí chuyển. - [An LLM API without vendor lock-in](https://anyrouter.dev/blog/llm-api-without-vendor-lock-in): Vendor 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. - [一份没有供应商锁定的 LLM API](https://anyrouter.dev/blog/zh/llm-api-without-vendor-lock-in): LLM API 的锁定通常不是模型本身——而是你对着写的那套专有客户端形状。站在标准兼容 OpenAI 的表面上（外加 Anthropic /messages 和 OpenAI /responses），出口一直开着：你写的同一份代码，直接指向源供应商也能跑。 - [API LLM không bị vendor lock-in](https://anyrouter.dev/blog/vi/llm-api-without-vendor-lock-in): Lock-in với API LLM thường không phải mô hình — mà là hình dạng client độc quyền bạn đã dựng. Đứng trên bề mặt chuẩn tương thích OpenAI (cộng Anthropic /messages và OpenAI /responses) giữ cửa thoát mở: cùng code bạn viết cũng chạy khi trỏ thẳng vào nhà cung cấp gốc. - [How automatic failover works in an LLM gateway](https://anyrouter.dev/blog/llm-gateway-latency-and-failover): A 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. - [LLM 网关里的自动 failover 怎么工作](https://anyrouter.dev/blog/zh/llm-gateway-latency-and-failover): 一次直连供应商调用只有一个失败点：一次限流、一次宕机、他们那边一次糟糕的发布，你的请求就失败。下面是 AnyRouter 实际用来绕开的机制——断路器、逐级冷却、以及回退链——以及为什么多出来的那一跳，相对模型生成时间几乎感觉不到。 - [Failover tự động trong LLM gateway hoạt động thế nào](https://anyrouter.dev/blog/vi/llm-gateway-latency-and-failover): Một call nhà cung cấp đơn có một điểm thất bại: một rate limit, một outage, một deploy xấu phía họ, và request của bạn fail. Đây là cơ chế AnyRouter thực sự dùng để đi vòng — circuit breaker, cooldown leo thang, và chuỗi fallback — và vì sao hop thêm gần như không đáng kể so với thời gian generate của mô hình. - [Building an LLM gateway on Cloudflare Workers](https://anyrouter.dev/blog/building-an-llm-gateway-on-cloudflare-workers): AnyRouter 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. - [在 Cloudflare Workers 上做 LLM 网关](https://anyrouter.dev/blog/zh/building-an-llm-gateway-on-cloudflare-workers): AnyRouter 跑在一组 Cloudflare Worker 上，不是常驻服务器。这套设计被具体限制卡住：128MB 内存上限禁止缓冲整段响应，3MiB 脚本上限逼出多 Worker 拆分，以及硬规则——每条上游调用都必须走 Cloudflare AI Gateway。下面是这套架构实际长什么样。 - [Xây LLM gateway trên Cloudflare Workers](https://anyrouter.dev/blog/vi/building-an-llm-gateway-on-cloudflare-workers): AnyRouter chạy trên một cụm Cloudflare Worker, không phải server sống lâu. Thiết kế bị ràng buộc cụ thể: trần 128MB RAM cấm buffer cả response, trần script 3MiB buộc tách nhiều Worker, và quy tắc cứng — mọi cuộc gọi upstream đều đi qua Cloudflare AI Gateway. Đây là kiến trúc thực tế. - [What developers actually route through AnyRouter](https://anyrouter.dev/blog/what-developers-actually-route): The 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. - [开发者真正经 AnyRouter 打出去的流量长什么样](https://anyrouter.dev/blog/zh/what-developers-actually-route): 目录有 170+ 个模型、28+ 家供应商，但流量不是这样铺开的。少数模型吃掉几乎全部免费档请求，模型数量也偏向少数 owner 组织，而且多数请求根本不带供应商名——它们按哪个 coding agent 发来打标。下面是目录的形状，以及人们真正调用的形状。 - [Developer thực sự route gì qua AnyRouter](https://anyrouter.dev/blog/vi/what-developers-actually-route): Catalog có 170+ mô hình trên 28+ nhà cung cấp, nhưng traffic không trải đều. Một nắm mô hình nuốt gần hết volume free-tier, số mô hình lệch về vài tổ chức owner, và hầu hết request chẳng nêu tên nhà cung cấp — chúng được gắn theo coding agent nào gửi. Đây là hình dạng catalog và hình dạng những gì người ta thực sự gọi. - [One API for every LLM](https://anyrouter.dev/blog/one-api-every-llm): One 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. - [一个 API 打到每个 LLM](https://anyrouter.dev/blog/zh/one-api-every-llm): 一个兼容 OpenAI 的端点打到目录里每个模型——170+ 个模型用 provider/model 寻址，上游自动失败切换、路由预设和流式。把现有客户端指到 AnyRouter，换模型改字符串，不用重写。 - [Một API cho mọi LLM](https://anyrouter.dev/blog/vi/one-api-every-llm): Một endpoint tương thích OpenAI tới mọi mô hình trong catalog — 170+ mô hình địa chỉ provider/model, failover tự động giữa upstream, preset routing và streaming. Chỉ client sẵn có vào AnyRouter và đổi mô hình bằng một chuỗi, không viết lại. - [BYOK: bring your own keys to every provider](https://anyrouter.dev/blog/byok-bring-your-own-keys): Attach 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. - [BYOK：把你自己的 key 接到每家供应商](https://anyrouter.dev/blog/zh/byok-bring-your-own-keys): 挂上你已经在付的 OpenAI、Anthropic、Google 和 60+ 其他供应商 key，经一个兼容 OpenAI 的 URL 路由，$0 加价，按 key 封顶花费——如果把闲置额度捐进共享池，最多拿回 8%，并且只要捐出的 key 还活着，就能免费开通 Go。 - [BYOK: mang key của bạn tới mọi nhà cung cấp](https://anyrouter.dev/blog/vi/byok-bring-your-own-keys): Gắn key OpenAI, Anthropic, Google và 60+ nhà cung cấp khác bạn đã trả, route qua một URL tương thích OpenAI với $0 markup, trần chi tiêu mỗi key, và — nếu donate quota nhàn rỗi vào shared pool — nhận lại tới 8% và mở Go miễn phí khi key được donate còn hoạt động. - [Run coding agents through one gateway](https://anyrouter.dev/blog/coding-agents-one-gateway): Point 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. - [让 coding agent 走同一个网关](https://anyrouter.dev/blog/zh/coding-agents-one-gateway): 把 Claude Code、Codex、OpenCode、Cursor 或任何兼容 OpenAI 的工具指到 AnyRouter，一把 key 打到每个模型，统一账单、按请求审计日志和 app 归因。两个环境变量——或者一条 npx 命令配 anyr CLI launcher。 - [Chạy coding agent qua một gateway](https://anyrouter.dev/blog/vi/coding-agents-one-gateway): Chỉ Claude Code, Codex, OpenCode, Cursor, hoặc bất kỳ công cụ tương thích OpenAI vào AnyRouter và có một key cho mọi mô hình, billing thống nhất, audit log mỗi request, và app attribution. Hai biến môi trường — hoặc một lệnh npx với anyr CLI launcher. - [An MCP gateway with managed server access](https://anyrouter.dev/blog/mcp-gateway-managed-servers): AnyRouter 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. - [带托管服务访问的 MCP 网关](https://anyrouter.dev/blog/zh/mcp-gateway-managed-servers): AnyRouter 跑一个 Model Context Protocol 服务器，把工作区——模型、key、预设、额度、状态——暴露成 JSON-RPC 工具，带 OAuth 2.1 鉴权，以及控制台 MCP Gateway 做托管访问。任何 MCP 客户端都能连的一个端点。 - [MCP gateway với truy cập server được quản lý](https://anyrouter.dev/blog/vi/mcp-gateway-managed-servers): AnyRouter chạy một Model Context Protocol server, lộ workspace — mô hình, key, preset, credit và trạng thái — thành công cụ JSON-RPC, auth OAuth 2.1, và MCP Gateway trên dashboard cho truy cập được quản lý. Một endpoint mọi MCP client có thể kết nối. - [A unified AI API: one endpoint, every provider dialect](https://anyrouter.dev/blog/unified-ai-api-one-endpoint): OpenAI 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. - [统一 AI API：一个端点，每家供应商的方言](https://anyrouter.dev/blog/zh/unified-ai-api-one-endpoint): OpenAI 出 /chat/completions，Anthropic 出 /messages，OpenAI 较新的表面是 /responses。统一 AI API 在一个 URL 上说完这些，你已有的客户端库继续工作——换 base URL，不换代码。 - [Unified AI API: một endpoint, mọi dialect nhà cung cấp](https://anyrouter.dev/blog/vi/unified-ai-api-one-endpoint): OpenAI ship /chat/completions, Anthropic ship /messages, bề mặt mới hơn của OpenAI là /responses. Unified AI API nói cả ba tại một URL, nên thư viện client bạn đã dùng vẫn chạy — bạn đổi base URL, không đổi code. - [An OpenAI API alternative that keeps your OpenAI code](https://anyrouter.dev/blog/openai-api-alternative): Looking 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. - [一套保住 OpenAI 代码的 OpenAI API 替代](https://anyrouter.dev/blog/zh/openai-api-alternative): 在找兼容 OpenAI 的 API 替代？留下 OpenAI SDK 和代码——换一个 base URL，打到每家供应商（包括 OpenAI 自己），自动故障切换，以及你已付费的 key 上 $0 markup 的 BYOK。 - [Thay thế OpenAI API mà giữ nguyên code OpenAI](https://anyrouter.dev/blog/vi/openai-api-alternative): Tìm API thay thế tương thích OpenAI? Giữ SDK và code OpenAI — đổi một base URL, tới mọi nhà cung cấp (kể cả OpenAI), failover tự động, và BYOK markup $0 trên key bạn đã trả. - [OpenRouter alternatives 2026: how AnyRouter differs](https://anyrouter.dev/blog/openrouter-alternative-anyrouter): OpenRouter 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. - [OpenRouter alternatives 2026：AnyRouter 差在哪](https://anyrouter.dev/blog/zh/openrouter-alternative-anyrouter): OpenRouter alternatives 2026，没有编造排名：AnyRouter 是一种 OpenRouter 替代——$0 加价 BYOK、捐赠共享池、$2/月 Go、Cloudflare 边缘路由、经 local relay 的端侧模型、内置 MCP，以及开放定价配置。 - [OpenRouter alternatives 2026: AnyRouter khác chỗ nào](https://anyrouter.dev/blog/vi/openrouter-alternative-anyrouter): OpenRouter alternatives 2026, không xếp hạng bịa: AnyRouter là một thay thế OpenRouter với BYOK markup $0, pool dùng chung được góp, gói Go $2/tháng, routing cạnh Cloudflare, model trên máy qua local relay, MCP server sẵn, và config giá mở. - [The top website for free LLM models — and how they're actually free](https://anyrouter.dev/blog/top-free-models-api): AnyRouter 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 daily tier, the donated shared pool, and self-hosted on-device models. - [免费 LLM 模型的首选站点——以及它们究竟如何免费](https://anyrouter.dev/blog/zh/top-free-models-api): AnyRouter 在 170+ 目录模型上提供真正的免费 LLM API。下面是人们实际免费路由到的模型，以及让它免费的三种诚实机制：anyrouter/free 日额度、捐赠共享池，以及自托管的端侧模型。 - [Trang hàng đầu cho mô hình LLM miễn phí — và chúng miễn phí thế nào](https://anyrouter.dev/blog/vi/top-free-models-api): AnyRouter phục vụ API LLM miễn phí thật trên 170+ mô hình catalog. Đây là thứ người ta thật sự route miễn phí, và ba cơ chế trung thực làm nó miễn phí: tầng ngày anyrouter/free, pool dùng chung từ key góp, và mô hình on-device tự host. - [Free models, just $2 a month](https://anyrouter.dev/blog/free-models-one-dollar): AnyRouter's Go plan is $2/mo: a $4 monthly credit plus free-model access. Or go free three ways — donate a provider key and Go costs nothing, use the anyrouter/free daily tier, or run models on your own device via local relay. - [免费模型，每月只需 $2](https://anyrouter.dev/blog/zh/free-models-one-dollar): AnyRouter 的 Go 套餐是 $2/月：每月 $4 额度，外加免费模型。也可以三条路完全免费——捐一把供应商 key 则 Go 不花钱、用 anyrouter/free 日额度，或通过 local relay 在自己的设备上跑模型。 - [Mô hình miễn phí, chỉ $2 mỗi tháng](https://anyrouter.dev/blog/vi/free-models-one-dollar): Gói Go của AnyRouter là $2/tháng: $4 credit hàng tháng cộng quyền dùng mô hình miễn phí. Hoặc miễn phí theo ba cách — góp một key nhà cung cấp thì Go không mất tiền, dùng hạn mức ngày anyrouter/free, hoặc chạy mô hình trên máy mình qua local relay. - [The most-used free models on AnyRouter so far](https://anyrouter.dev/blog/most-used-free-models): We 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. - [目前 AnyRouter 上用得最多的免费模型](https://anyrouter.dev/blog/zh/most-used-free-models): 我们从网关拉了真实用量：大家实际打到哪些免费模型。GLM-5.2 遥遥领先，gpt-4o-mini 是紧随其后的干活模型，anyrouter/free 默默扛着长尾。下面的数字直接来自生产。 - [Các mô hình miễn phí được dùng nhiều nhất trên AnyRouter đến nay](https://anyrouter.dev/blog/vi/most-used-free-models): Chúng tôi lấy usage thật từ gateway: mô hình miễn phí nào người ta thực sự route tới. GLM-5.2 bỏ xa, gpt-4o-mini là ngựa thồ phía sau, anyrouter/free âm thầm phục vụ đuôi dài. Số liệu bên dưới, thẳng từ production. - [Apple's on-device Foundation Model, now on the AnyRouter API](https://anyrouter.dev/blog/apple-foundation-models-on-device): Run 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. - [Apple 设备端 Foundation Model，现已接入 AnyRouter API](https://anyrouter.dev/blog/zh/apple-foundation-models-on-device): 在自己的 Mac 上跑 Apple Intelligence 的设备端 Foundation Model，用你平时打其他模型的同一套 AnyRouter API 来调。Prompt 留在本机，token 不花钱，也没有供应商账号要管。 - [Foundation Model trên thiết bị của Apple, nay trên API AnyRouter](https://anyrouter.dev/blog/vi/apple-foundation-models-on-device): Chạy Foundation Model trên thiết bị của Apple Intelligence trên Mac của bạn và gọi nó qua cùng API AnyRouter bạn dùng cho mọi thứ khác. Prompt ở lại trên phần cứng, bạn không trả token, không có tài khoản nhà cung cấp phải quản lý. - [Go on AnyRouter for $2 — or free if you donate a key](https://anyrouter.dev/blog/starter-plan-one-dollar): Go is now $2/mo: a $4 monthly credit plus free-model access (1,000 requests/day), no card surprises. Donate one working provider key to the shared pool instead, and Go costs nothing at all. - [AnyRouter 的 Go：$2，或捐一把 key 就免费](https://anyrouter.dev/blog/zh/starter-plan-one-dollar): Go 现在是 $2/月：每月 $4 额度，外加免费模型（每天 1000 次），没有卡上意外。也可以向共享池捐一把还能用的供应商 key，Go 完全不花钱。 - [Go trên AnyRouter $2 — hoặc miễn phí nếu góp một key](https://anyrouter.dev/blog/vi/starter-plan-one-dollar): Go hiện $2/tháng: $4 credit hàng tháng cộng mô hình miễn phí (1.000 request/ngày), không bất ngờ trên thẻ. Thay vào đó góp một key nhà cung cấp còn dùng được vào pool chung thì Go không tốn gì. - [Donate an idle provider key, earn credits back: a walkthrough](https://anyrouter.dev/blog/shared-key-pool): Hold 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. - [捐一把闲置供应商 key，赚回额度：逐步说明](https://anyrouter.dev/blog/zh/shared-key-pool): 手里有一把还有余量的供应商 key？两下点击就能捐进共享池。池子经你的 key 打出去的每个 token，都会按名义成本给你记 pending 额度——按套餐最高 8%——随时 claim，也可以开 auto-claim。下面是逐步操作。 - [Góp một key nhà cung cấp đang dư, nhận lại credit: từng bước](https://anyrouter.dev/blog/vi/shared-key-pool): Có key nhà cung cấp còn dư hạn mức? Hai lần bấm là góp vào pool dùng chung. Mỗi token pool phục vụ qua key của bạn ghi pending credit — tối đa 8% chi phí danh nghĩa, theo gói — claim bất lúc nào hoặc bật auto-claim. Đây là từng bước. - [Bring your own keys — every provider behind one API](https://anyrouter.dev/blog/bring-your-own-keys): Connect 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. - [自带 Key——所有供应商，一个 API](https://anyrouter.dev/blog/zh/bring-your-own-keys): 把你已经在付的供应商 key 和订阅接进来，经一个 OpenAI 兼容 URL 自动失败切换，并且——很快——把闲置配额捐进共享池还能拿回额度。 - [Mang key của bạn — mọi nhà cung cấp sau một API](https://anyrouter.dev/blog/vi/bring-your-own-keys): Nối các key và gói nhà cung cấp bạn đã trả, route qua một URL tương thích OpenAI với failover tự động, và — sắp tới — nhận credit lại khi góp quota nhàn vào pool chung. - [A clearer way to pay: Free, Standard, and pay-as-you-go](https://anyrouter.dev/blog/billing-redesign): We 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. - [更清楚的付费方式：Free、Standard，以及按量](https://anyrouter.dev/blog/zh/billing-redesign): 我们把计费拆成简单的订阅档和独立的按量额度，这样你始终知道在付什么、每次请求花多少。 - [Cách trả tiền rõ hơn: Free, Standard, và trả theo mức dùng](https://anyrouter.dev/blog/vi/billing-redesign): Chúng tôi tách billing thành tầng đăng ký đơn giản và credit trả theo mức dùng riêng, để bạn luôn biết đang trả gì và mỗi request tốn bao nhiêu. - [Free LLM API: 150+ models with a real free tier](https://anyrouter.dev/blog/free-llm-api): You don't need a credit card to start building with large language models. A free LLM API should give you real models, an OpenAI-compatible endpoint, and a way to keep costs at zero as you grow — here's how that works in practice. - [免费 LLM API：150+ 模型，真正的免费档](https://anyrouter.dev/blog/zh/free-llm-api): 开始用大语言模型不必先绑卡。一个像样的免费 LLM API 该给你真模型、兼容 OpenAI 的端点，以及用量涨了还能把成本留在零的办法——下面讲实际怎么做。 - [API LLM miễn phí: 150+ mô hình với free tier thật](https://anyrouter.dev/blog/vi/free-llm-api): Bạn không cần thẻ để bắt đầu dựng với mô hình ngôn ngữ lớn. Một API LLM miễn phí nên cho mô hình thật, endpoint tương thích OpenAI, và cách giữ chi phí ở zero khi lớn — đây là cách nó chạy trên thực tế. - [Is there an unlimited free LLM API? An honest answer](https://anyrouter.dev/blog/unlimited-free-llm-api): Truly unlimited and truly free can't both be true forever — someone pays for the GPUs. But you can get very close: free tiers, your own provider quota at $0 markup, and a shared key pool. Here's how each one works. - [有没有无限免费的 LLM API？诚实回答](https://anyrouter.dev/blog/zh/unlimited-free-llm-api): 真正无限和真正免费不可能永远同时成立——GPU 总有人付钱。但你可以非常接近：免费档、你自己的供应商配额加 $0 加价，以及共享 key 池。下面是每一条怎么工作。 - [Có API LLM miễn phí không giới hạn không? Trả lời thành thật](https://anyrouter.dev/blog/vi/unlimited-free-llm-api): Thật sự không giới hạn và thật sự miễn phí không thể cùng đúng mãi — ai đó trả GPU. Nhưng bạn có thể rất gần: free tier, quota nhà cung cấp của bạn markup $0, và pool key dùng chung. Đây là từng cái chạy thế nào. - [Unify every LLM API behind one endpoint](https://anyrouter.dev/blog/unify-llm-api): OpenAI, Anthropic, Google, and a dozen others each ship a different SDK, auth scheme, and error shape. Unifying them behind one OpenAI-compatible API turns model choice into a config value instead of an integration project. - [把每家 LLM API 统一到一个端点后面](https://anyrouter.dev/blog/zh/unify-llm-api): OpenAI、Anthropic、Google 以及十多家各自出一套 SDK、鉴权和错误形状。把它们统一到一个兼容 OpenAI 的 API 后面，选模型就变成配置值，而不是一次集成项目。 - [Thống nhất mọi LLM API sau một endpoint](https://anyrouter.dev/blog/vi/unify-llm-api): OpenAI, Anthropic, Google, và hàng tá hãng khác mỗi nhà một SDK, auth, và hình lỗi khác. Thống nhất chúng sau một API tương thích OpenAI biến chọn model thành giá trị config, không phải dự án tích hợp. - [Unify your MCP tools behind one free gateway](https://anyrouter.dev/blog/unify-mcp-gateway-free): As you add MCP servers — for search, code, data, your own internal tools — each client needs its own config and credentials. A unified MCP gateway puts them behind one endpoint with one auth flow, and connecting to AnyRouter's is free. - [把 MCP 工具统一到一个免费网关后面](https://anyrouter.dev/blog/zh/unify-mcp-gateway-free): 当你不断加 MCP 服务器——搜索、代码、数据、自己的内部工具——每个客户端都要自己的配置和凭证。统一 MCP 网关把它们放在一个端点、一套鉴权后面，连上 AnyRouter 的网关是免费的。 - [Thống nhất công cụ MCP sau một gateway miễn phí](https://anyrouter.dev/blog/vi/unify-mcp-gateway-free): Khi bạn thêm MCP server — tìm kiếm, code, data, công cụ nội bộ — mỗi client cần config và credential riêng. MCP gateway thống nhất đặt chúng sau một endpoint với một luồng auth, và kết nối tới gateway của AnyRouter thì miễn phí. - [OpenRouter alternative: what to compare before you switch](https://anyrouter.dev/blog/openrouter-alternative): Looking for an OpenRouter alternative? Compare markup, bring-your-own-keys, billing, and lock-in — then see where AnyRouter lands. No invented benchmarks. - [OpenRouter 替代：换网关前该比什么](https://anyrouter.dev/blog/zh/openrouter-alternative): 在找 OpenRouter 替代？比加价、自带 key、账单和锁定——再看 AnyRouter 落在哪。没有编造的榜单。 - [Thay thế OpenRouter: so gì trước khi chuyển](https://anyrouter.dev/blog/vi/openrouter-alternative): Đang tìm thay thế OpenRouter? So markup, bring-your-own-keys, billing, và lock-in — rồi xem AnyRouter đứng ở đâu. Không bịa benchmark. ## Model releases - [Model releases](https://anyrouter.dev/blog/releases): Changelog of models added or disabled, newest first. - [Claude Sonnet 5.5](https://anyrouter.dev/blog/releases/2026-09-29): Anthropic's Claude Sonnet 5.5 joins the catalog — the direct upgrade to Claude Sonnet 5, at the same $2 / $10 per million input / output tokens, with adaptive thinking on by default, 1M-token context, 128K max output, and vision input. - [Step 5 Preview](https://anyrouter.dev/blog/releases/2026-09-29-step-5): StepFun's next-generation flagship base model joins the catalog BYOK-only on AIHubMix — 1M-token context, 64K max output, text/image/video input, and adjustable reasoning at $1.08 / $3.0888 per million input / output tokens. - [BGE-M3, BGE Multilingual Gemma 2, Mistral Small 3.2 — now on OVHcloud AI Endpoints](https://anyrouter.dev/blog/releases/2026-09-27): Two BAAI multilingual embedding models and Mistral's current 24B instruction model join the catalog, both on a new BYOK provider: OVHcloud AI Endpoints. - [Kev 4B](https://anyrouter.dev/blog/releases/2026-09-26): Kev 4B is a small open-weight decision model — a LoRA adapter and pointer head on Qwen3.5-4B-Base. It answers typed questions about a state with calibrated probabilities instead of generated text, on the same native `/v1/decisions` contract as the rest of the family. - [Decisions family + anyr decision](https://anyrouter.dev/blog/releases/2026-09-25): Fastino GLiNER2.5-Decide joins TypeSafe Jev and the anyrouter/decision preset, while the new `anyr decision` command gives the whole Decisions family a native terminal client instead of a chat-agent launcher. - [LongCat-2.5-Preview](https://anyrouter.dev/blog/releases/2026-09-25-longcat-2-5-preview): Meituan's LongCat-2.5-Preview — a ~1.6T-parameter MoE with ~48B active, 1M-token context, image understanding, and a thinking toggle — joins the catalog over the official LongCat API, BYOK. - [Space Bunny Alpha](https://anyrouter.dev/blog/releases/2026-09-24): Space Bunny Alpha — an anonymous frontier-class stealth preview with blazing-fast inference, strong coding performance, and native multimodal input — joins the catalog as a free model. It always reasons with adjustable effort over a 1M-token context window, served $0 via OpenRouter, Nous, and OpenCode Zen platform hops. - [Verified AIHubMix BYOK models](https://anyrouter.dev/blog/releases/2026-09-24-aihubmix): Five verified text-output models join the catalog through AIHubMix and other BYOK routes: Qwen3 235B A22B Instruct 2507, Mercury 2.5, L3.1 Euryale 70B, GPT-6 Sol, and GPT-6 Luna. Published provider prices and context windows are recorded per upstream; AnyRouter does not add platform markup to BYOK traffic. - [Union Alpha disabled](https://anyrouter.dev/blog/releases/2026-09-23-disabled): Previously verified platform routes return 404 for stealth/union-alpha. Hidden from the catalog; configured BYOK fallbacks remain available for users who saved keys. - [Claude Opus 5.5](https://anyrouter.dev/blog/releases/2026-09-22): Anthropic's Claude Opus 5.5 — the successor to Claude Opus 5 for long-running agentic coding and knowledge work — joins the catalog. It delivers Fable 5.1-level performance at 40% lower cost ($4 / $20 per million input / output tokens), with adaptive thinking always on, 1M-token context, vision input, and tool use. - [Grok 4.7](https://anyrouter.dev/blog/releases/2026-09-21): xAI's Grok 4.7 joins the catalog — 500K context, adjustable reasoning, vision in, and six BYOK upstream routes. - [Llama Nemotron Embed VL 1B v2 disabled](https://anyrouter.dev/blog/releases/2026-09-17-disabled): NVIDIA's hosted NIM API returns 404 for this catalog id. The model is downloadable self-host NIM only. The live NVIDIA embedding SKU is nvidia/nemotron-3-embed-1b. - [Union Alpha now on AnyRouter](https://anyrouter.dev/blog/releases/2026-09-16-union-alpha): Stealth preview Union Alpha joins the catalog free — multimodal research, coding, and agentic workflows at $0. - [Agnes 3.0 Flash and Nemotron Parse 2.0](https://anyrouter.dev/blog/releases/2026-09-15): Agnes AI's Agnes 3.0 Flash (512K, vision in, text out) and NVIDIA Nemotron Parse 2.0 (document images in, structured markdown out) join the catalog. - [AIHubMix BYOK hops on DeepSeek V4.1 Flash, Solar Pro 4, and GPT-6 Astra](https://anyrouter.dev/blog/releases/2026-09-15-aihubmix-byok): Existing listings pick up an aihubmix-byok hop. Same catalog ids — not new SKUs. Platform aihubmix stays off (#3031). - [Context-window floors on anyrouter/auto, free, byok, and the other virtual ids](https://anyrouter.dev/blog/releases/2026-09-15-virtual-context): Append [1m] or [500k] to any first-party virtual id to keep only members with at least that context window. Not a new listing — the same preset, with a token floor. - [Poolside platform route disabled](https://anyrouter.dev/blog/releases/2026-09-15-upstream): The Poolside platform key returns HTTP 429 usage limit exceeded. Listings stay: poolside/laguna-s-2.1, poolside/laguna-xs-2.1, poolside/laguna-m.1, poolside/laguna-xs.2 — not new SKUs. Platform poolside is off; hops parked. poolside-byok stays live. - [Ling-3.0-flash-VL, Sante, Fin, and OpenRouter :free hops](https://anyrouter.dev/blog/releases/2026-09-13): inclusionAI Ling-3.0-flash-VL, Sante, and Fin join the catalog, plus Nex-N2.5 Mini/Pro. OpenRouter :free is the wire and an alias — Nemotron 3 Ultra and Inkling Small pick up hue hops so we can burn remaining free quota. - [DeepSeek V4.1 Flash](https://anyrouter.dev/blog/releases/2026-09-10): DeepSeek V4.1 Flash joins the catalog as deepseek/deepseek-v4.1-flash, with official DeepSeek API and OpenRouter BYOK hops. Peak list $0.30 / $1.20 per 1M tokens. - [2 models disabled](https://anyrouter.dev/blog/releases/2026-09-07-disabled): Caugiay backend disabled 2026-09-07 (#3146/#2871) — HTTP 401; this model's only platform upstream was caugiay. Plus 1 more. - [Caugiay and SambaNova platform routes disabled](https://anyrouter.dev/blog/releases/2026-09-07-upstream): The Caugiay platform key returns HTTP 401 Access denied, and the SambaNova platform account requires a payment method (HTTP 402). BYOK SambaNova stays live; Caugiay has no BYOK sibling. NVIDIA NIM hops that 404 for models NVIDIA does not serve were dropped per listing, not the whole nvidia backend. - [Claude Fable 5.1 and GPT-6 Astra on Experiential](https://anyrouter.dev/blog/releases/2026-09-05): Experiential Cloud promotional hops for Claude Fable 5.1 and a new GPT-6 Astra listing (BYOK live; hosted platform hop pending #2842 recert). - [Pareto disabled](https://anyrouter.dev/blog/releases/2026-09-05-disabled): Cloudflare AI Gateway Unified Billing is exhausted (#3121), so the platform cloudflare backend is disabled. Keep the verified unbiased/pareto model as a disabled catalog tombstone until the backend is funded and re-enabled. - [Muse Spark 1.3](https://anyrouter.dev/blog/releases/2026-09-04): Meta's Muse Spark 1.3 joins the catalog over AIHubMix BYOK — a multimodal reasoning model for agentic tasks with a 1M-token context window. - [Gemini 3.8 Flash and Mercury 2.5 Preview](https://anyrouter.dev/blog/releases/2026-09-03): Google Gemini 3.8 Flash and Inception Labs Mercury 2.5 Preview join the catalog. Claude Fable 5.1 and Qwen3.8 Max pick up AIHubMix hops on their existing ids. - [Ox Alpha disabled](https://anyrouter.dev/blog/releases/2026-09-03-disabled): This model has been removed. Requests that still use stealth/ox-alpha or stealth/ox-alpha[1m] are routed to anyrouter/auto. - [Claude Fable 5.1](https://anyrouter.dev/blog/releases/2026-09-02): Anthropic Claude Fable 5.1 joins the catalog as one listing, routed through Anthropic BYOK and Cloudflare Workers AI, with OpenRouter BYOK as a fallback. - [Hy4 Preview on AIHubMix BYOK](https://anyrouter.dev/blog/releases/2026-09-02-hy4-preview): Tencent Hunyuan Hy4 Preview joins the catalog as tencent/hy4-preview, routed through AIHubMix BYOK at the aggregator's published list rates. - [Qwen3.8 Flash on AnyRouter](https://anyrouter.dev/blog/releases/2026-09-02-qwen3-8-flash): Alibaba Qwen3.8 Flash via AIHubMix BYOK. List $0.1126 / $0.38 per 1M. - [2 models disabled](https://anyrouter.dev/blog/releases/2026-09-01-disabled): Every remaining platform host returns 404 for this catalog id. NVIDIA's current Nano omni/VL successor is nvidia/nemotron-3-nano-omni-30b-a3b-reasoning. Plus 1 more. - [Hy3 disabled](https://anyrouter.dev/blog/releases/2026-08-28-disabled): Hosted probes for this catalog id fail with a bad request. The model is unlisted rather than advertised as a live hosted chat model. - [5 models disabled](https://anyrouter.dev/blog/releases/2026-08-27-disabled): The remaining platform host is out of credit, and the other platform route is already disabled. Remaining routes require a user-owned key, so the model is unlisted rather than advertised as a live hosted chat model. Plus 4 more. - [Catalog sweep — GLM-5.3, vision, Agnes, Sol Disc](https://anyrouter.dev/blog/releases/2026-08-26-catalog-sweep): Eight models from the post-closeout sweep: Z.AI GLM-5.3 (coding preview), DeepSeek vision + 0731-fast, Microsoft MAI-Thinking-1, OpenAI GPT-5.6 Sol Disc, and Agnes 2.5 Flash/Pro/Alpha via AIHubMix. - [GLM-5.3-Flash — Ox Alpha, named](https://anyrouter.dev/blog/releases/2026-08-26-glm-5-3-flash): The Ox Alpha preview is GLM-5.3-Flash: native multimodal, 1M context, MIT-licensed 320B-A18B. Same AnyRouter routes, catalog id z-ai/glm-5.3-flash. - [Qwen3.8-Flash-Next from Empero](https://anyrouter.dev/blog/releases/2026-08-26-qwen3-8-flash-next-fp8): Free community endpoint for Qwen3.8-Flash-Next — open by default, from Empero research lab. Catalog id qwen/qwen3.8-flash-next. - [AIHubMix free tier — 15 more $0 routes](https://anyrouter.dev/blog/releases/2026-08-25-aihubmix-free): AIHubMix joins the platform free pool: MiniMax M2.7, Kimi K3, Gemini 3.x Flash, Nemotron 3, GPT-OSS 20B, and more, all routed at $0. - [2 models disabled](https://anyrouter.dev/blog/releases/2026-08-24-disabled): The only platform host (hoian) is balance-quarantined and no longer serves this catalog id reliably. Unlisted until a live hosted path returns. Plus 1 more. - [Ox Alpha](https://anyrouter.dev/blog/releases/2026-08-21-ox-alpha): Ox Alpha joins the catalog free — a stealth reasoning model for coding, agentic work, and long-horizon engineering. - [Qwen 27B dense SKUs and Llama 3.3 70B Instruct](https://anyrouter.dev/blog/releases/2026-08-20): Qwen3.6-27B, Qwen3.8-27B, Gemma 3 27B IT, and Meta Llama 3.3 70B Instruct join the catalog as paid chat models. - [Qwen3.8-27B and DeepSeek V4 Flash, 50% off](https://anyrouter.dev/blog/releases/2026-08-20-qwen3-8-27b-sale): Half off through 1 Sep. Same ids, same API — just a friendlier bill. - [12 models disabled](https://anyrouter.dev/blog/releases/2026-08-19-disabled): The platform Workers AI host no longer serves this catalog id (model_unavailable). Remaining routes require a user-owned key, so the model is unlisted rather than advertised as a live hosted chat model. Plus 11 more. - [Mistral 7B Instruct v0.1 disabled](https://anyrouter.dev/blog/releases/2026-08-18-disabled): Cloudflare Workers AI retired this SKU on 2026-05-30; live smoke 2026-08-14/18 returns model_unavailable (no_route). It was this model's only upstream, so it was disabled rather than the route pruned. - [GitHub Models platform and BYOK routes disabled](https://anyrouter.dev/blog/releases/2026-08-18-upstream): GitHub Models was fully retired on 2026-07-30. The inference API and BYOK endpoints return HTTP 410, so the github and github-byok backends are off. - [DeepSeek V4 Pro](https://anyrouter.dev/blog/releases/2026-08-17): DeepSeek V4 Pro (0813) joins the catalog, hosted on Cloudflare Workers AI with a 1M-token context window. - [4 models disabled](https://anyrouter.dev/blog/releases/2026-08-17-disabled): Cloudflare has not published per-token pricing for this partner-hosted SKU (rate visible only in the CF dashboard once provisioned); shipping it live on the metered `cloudflare` backend without a real rate would bill $0. Plus 3 more. - [Gemini 3.7 Flash and latest frontier chat SKUs](https://anyrouter.dev/blog/releases/2026-08-14): Google Gemini 3.7 Flash joins the catalog, plus Qwen3.8 2.4T A95B, Muse Spark 1.2, Inkling Small, Solar Pro 4, Seed 2.1 Turbo, Seed 2.0 Code, Claude Opus 5 Fast, and Dots3-Note Preview. - [5 models disabled](https://anyrouter.dev/blog/releases/2026-08-14-disabled): CF Workers AI LoRA host 404 / model_unavailable on every smoke probe (2026-08-14). Canonical Gemma instruct SKUs remain (gemma-3 / gemma-4). Sibling gemma-2b-it-lora already disabled. Plus 4 more. - [7 models disabled](https://anyrouter.dev/blog/releases/2026-08-13-disabled): SiliconFlow no longer lists this id; its catalogue carries gemma-4-12B-it, gemma-4-26B-A4B-it and gemma-4-31B-it instead. Plus 6 more. - [Nemotron Lightning, Muse Glimmer, Seedance 2.5, DeepSeek NIM Flash](https://anyrouter.dev/blog/releases/2026-08-12): NVIDIA NIM additions (Nemotron 3.5 Lightning 30B, Meta Muse Glimmer 30B, DeepSeek-V4-Flash 0731), ByteDance Seedance 2.5 on Workers AI, and free Requesty route for Ling-3.0-tiny. - [Free-route expansion + Liquid LFM 2.5](https://anyrouter.dev/blog/releases/2026-08-12-free): Expanded free platform routes across NVIDIA Nemotron free models, GPT-OSS-20B free, Ling-3.0-tiny on Novita, and new Liquid LFM 2.5 2.6B free. CommandCode free/promo routes for Laguna S 2.1 and MiMo V2.5 Pro. - [Grok 4.6](https://anyrouter.dev/blog/releases/2026-08-12-grok-46): xAI Grok 4.6 joins the catalog via xAI BYOK and OpenRouter BYOK. 500K context, $2/$6 list on xAI. - [3 models disabled](https://anyrouter.dev/blog/releases/2026-08-12-disabled): The catalogue is text/embedding-output only; video models stay on disk for future re-enable (same posture as seedance-2.0-mini). Unpriced CF video would also fail metered-catalog-billing. Plus 2 more. - [EmbeddingGemma 300M and Ling-3.0-tiny](https://anyrouter.dev/blog/releases/2026-08-07): Google's EmbeddingGemma 300M open embedding model and inclusionAI's Ling-3.0-tiny free MoE chat model join the catalog. - [Sakana Namazu](https://anyrouter.dev/blog/releases/2026-08-03): Sakana AI's Japanese-specialized LLM (built on Kimi K2.6) joins the catalog via BYOK. - [Nemotron 3.5 Nano](https://anyrouter.dev/blog/releases/2026-08-01): NVIDIA's Nemotron 3.5 Nano joins the catalog via Blackbox AI BYOK. - [Nemotron Nano, GLM-4.5/4.6, MiniMax M2, Qwen3.5-9B/27B](https://anyrouter.dev/blog/releases/2026-07-31): Eight new models discovered from upstream providers and added to the catalog — NVIDIA's free Nemotron Nano 12B V2 VL and 9B V2 via OpenRouter, Z-AI's GLM-4.5 and GLM-4.6 (with vision variant), MiniMax M2, and Alibaba's Qwen3.5-9B and Qwen3.5-27B. - [Qwen3.7 Flash](https://anyrouter.dev/blog/releases/2026-07-29): Alibaba's Qwen3.7 Flash — a vision-language reasoning model for multimodal agents, visual coding, search, and computer interaction — joins the catalog via OpenRouter BYOK. - [16 models disabled](https://anyrouter.dev/blog/releases/2026-07-26-disabled): The catalogue was narrowed to models whose output is text or embeddings; this model's output is an image, so it was taken out of service. Related: #1551 (these SKUs bill $0 on a metered backend). Plus 15 more. - [Claude Opus 5](https://anyrouter.dev/blog/releases/2026-07-25): Anthropic's Claude Opus 5 — the flagship model for demanding reasoning, coding, and long-horizon agentic work — joins the catalog, BYOK-only like its Claude siblings. - [Ling-3.0-flash](https://anyrouter.dev/blog/releases/2026-07-24): inclusionAI's Ling-3.0-flash — a 124B-parameter Mixture-of-Experts model (~5.1B active) tuned for token-efficient, production-scale agentic inference — joins the catalog, served free with a user-owned API key (BYOK). - [Google unified-billing and Blackbox platform routes disabled](https://anyrouter.dev/blog/releases/2026-07-24-upstream): The Cloudflare AI Gateway unified-billing balance and the Blackbox platform budget both ran out. BYOK siblings stay live; platform traffic fails over or stops. - [Gemini 3.6 Flash & Gemini 3.5 Flash Lite](https://anyrouter.dev/blog/releases/2026-07-22): Google's Gemini 3.6 Flash and Gemini 3.5 Flash Lite join the catalog as partner-hosted SKUs on Cloudflare Workers AI, with OpenRouter BYOK fallback. - [Laguna S 2.1](https://anyrouter.dev/blog/releases/2026-07-21): Poolside's latest coding agent model Laguna S 2.1 (118B total, 8B active parameters, 1M context, 70.2% Terminal-Bench 2.1, 40.4% DeepSWE) joins the catalog — open-weight under OpenMDW-1.1. - [Inkling + Nemotron 3 Embed 1B](https://anyrouter.dev/blog/releases/2026-07-17): Thinking Machines Lab's first open-weights foundation model Inkling (975B MoE, 41B active, 1M context, multimodal input with switchable reasoning) and NVIDIA's Nemotron-3-Embed-1B multilingual embedding model (2048 dims, 34 languages) join the catalog via NVIDIA NIM. - [Kimi K3](https://anyrouter.dev/blog/releases/2026-07-16): Moonshot AI's Kimi K3 is now available on AnyRouter — an open-source model with a 1M-token context window and native visual understanding (text, image, and video). Built for long-horizon software engineering and deep reasoning where code meets visual and spatial thinking, with thinking mode always on. - [OpenAI and DeepInfra platform routes disabled](https://anyrouter.dev/blog/releases/2026-07-16-upstream): The platform OpenAI key has no quota (429 insufficient_quota) and DeepInfra has no payment method (402). BYOK users are unaffected. - [Named OpenRouter platform backend disabled](https://anyrouter.dev/blog/releases/2026-07-10-upstream): The public `openrouter` backend is off. Platform traffic uses the masked hue route; user keys stay on openrouter-byok. - [Grok 4.5 and Laguna XS 2.1](https://anyrouter.dev/blog/releases/2026-07-09): Two frontier additions: xAI's Grok 4.5 joins the catalog and Poolside ships a refreshed Laguna XS 2.1 coding model. - [Free-tier open models via SiliconFlow](https://anyrouter.dev/blog/releases/2026-07-08): A batch of open-weight models now has a free-tier upstream — Qwen3 across sizes, Gemma 4 27B, and Tencent Hy3. - [Claude Sonnet 5](https://anyrouter.dev/blog/releases/2026-07-02): Anthropic's Claude Sonnet 5 is available through BYOK — bring your Anthropic key and route it behind the gateway. - [Codex-class OpenAI models and GLM-5](https://anyrouter.dev/blog/releases/2026-07-01): The OpenAI Codex family lands — GPT-5.3 / 5.2 Codex and 5.1 Codex Max — alongside Z.ai's GLM-5 and Qwen3.7 Max. - [LongCat-2.0](https://anyrouter.dev/blog/releases/2026-06-30): The LongCat provider joins the catalog with LongCat-2.0, available via BYOK. - [Cerebras, Venice, and Wafer providers](https://anyrouter.dev/blog/releases/2026-06-24): Three new upstreams broaden coverage — Cerebras GPT-OSS, Venice's MiniMax M2.7, and Wafer's aggregated MiniMax M3 and GLM-5.2. - [13 models disabled](https://anyrouter.dev/blog/releases/undated-disabled): Its BYOK aggregator upstream no longer lists this model id (verify:upstreams MISSING 2026-07-16), and that was its only upstream. See #1283. Plus 12 more. ## Developer resources Machine-readable surfaces at predictable URLs: - [OpenAPI spec](https://anyrouter.dev/openapi.json): OpenAPI 3.1 for the whole `/api/v1` surface (also at https://anyrouter.dev/openapi.yaml). - [Docs index (markdown)](https://anyrouter.dev/docs.md): this documentation set as one markdown page. - [Model catalog (markdown)](https://anyrouter.dev/models.md): every model with pricing, context window, and links to `/model/.md` datasheets. - [Apps directory (markdown)](https://anyrouter.dev/data/apps.md): curated agent apps and their model routing. - [Data pages (markdown)](https://anyrouter.dev/data.md): leaderboards and benchmarks; each child page has a `.md` twin. - [Health](https://anyrouter.dev/api/v1/health): live status JSON for uptime checks. - [Contact](https://anyrouter.dev/contact): support, privacy, and security email channels. Official CLI (`anyr`) — native binary, no npm: ```bash curl -fsSL https://anyrouter.dev/setup.sh | bash anyr claude # launch Claude Code through AnyRouter anyr login ``` - [CLI docs](https://anyrouter.dev/docs/cli.md): full command reference for the launcher, profiles, delegation, and usage queries. ## Optional - [Full docs bundle](https://anyrouter.dev/llms-full.txt): Every doc concatenated into a single file.