AI API gateway

OpenRouter: one API and a shared credit balance for models from multiple providers. It combines an OpenAI-compatible interface with provider routing, automatic provider failover, optional model fallbacks, and response-level usage accounting. Teams can specify provider allowlists, require supported parameters, set maximum provider prices, and enforce zero-data-retention routing for inference. This reduces integration and routing work without claiming that all providers have identical capabilities or policies.

Put your full AI stack behind one key. Track and cap LLM spend, route to the right model, and self-host anywhere — even air-gapped. 140+ providers, 1,892 models, 53K+ GitHub stars. The AI Gateway for platform teams Put your full AI stack behind one key. See who is driving spend, cap it before it runs, and send each request to the model that should handle it. Start freeTalk to sales Self-host in minutes. No credit card. Your AI App Humans Agents Machines LiteLLM AI GATEWAY Optimization Observability Routing Governance LLMs MCPs Agents Run in production by the teams shipping AI at scale. Testimonial Testimonial “LiteLLM gives NVIDIA engineers a single, consistent way to access more than 100 AI model endpoints.” Ajay DograProduct, NVIDIA Testimonial Testimonial “LiteLLM streamlines the complexities of managing multiple LLM models.” Mark KoltnukPrincipal Architect, Lemonade Testimonial Testimonial “LiteLLM has let my team provide the latest LLM models to our users, usually within a day of them being released… it has saved us months of work.” David LeenStaff Software Engineer, Netflix Testimonial Testimonial “If we decide to switch the backend model, it’s a simple configuration update in the gateway; no code changes, procurement cycles, or repetitive security reviews required.” Dennis HenryProductivity Architect, Okta Testimonial Testimonial “After the company began using router provider LiteLLM, the costs of some advanced AI tasks such as coding fell by as much as 56%.” Mark AustinVP, AT&T Data Office Why LiteLLM Give your whole org access to every model, agent, and MCP, then see, control, and optimize every request. 01 Access: Give your whole company every model. Put every model, agent, and MCP behind one API and one login. We handle key management and work with the secret manager you already run, so platform teams open access to the whole org without becoming the bottleneck, and developers build in minutes, not a procurement cycle. One OpenAI-compatible API to 140+ providers and 1,800+ models. Swap models without changing app code. One login with SSO, scoped by team, project, or app. Day-zero support for new models, so developers get the latest the day it ships. Reach agents and MCP servers through the same gateway, not just LLMs. Bring your own internal, fine-tuned, and self-hosted models behind the same key. KeysCreate KeyEndpointsModelsTeamsTeamMembersMCPAI Hub Virtual Keys Ask AI Export + Create New KeyShowing 1–6 of 6Filters KeyTeamLast ActiveSpend / Budget acme-prod-gatewayActivesk-…9f2Aplatform-eng2 min ago$4,182.55 / $10,000 wayne-data-scienceActivesk-…Tt09data-science3 min ago$6,740.15 / $12,000 hooli-data-squadActivesk-…Pq77ai-gatewayjust now$3,301.42 / $8,000 globex-genai-platformActivesk-…7b01ml-platform5 min ago$1,905.20 / $5,000 ci-eval-runnerRate-limitedsk-…Hh55infra7 min ago$58.44 / $250 umbrella-eng-sandboxExpiredsk-…WW21security38 min ago$121.87 / $500 Rows per page: 6Page 1 of 1 Key Ownership Owned By YouService AccountAnother UserAgent New OrganizationAll Organizations TeamSearch or select a team Key Details *Key Namee.g. prod-gateway-key ModelsSelect models Leave empty to allow access to all models Key TypeAI APIs Optional Settings CancelCreate Key Team: All TeamsView: All8 deployments Public NameProviderModeInput / OutputHealth gpt-5openai/gpt-5OpenAIChat$1.25 / $10Healthy gpt-5-miniopenai/gpt-5-miniOpenAIChat$0.25 / $2Healthy claude-opus-4-8anthropic/claude-opus-4-8AnthropicChat$5 / $25Healthy claude-sonnet-4-5anthropic/claude-sonnet-4-5AnthropicChat$3 / $15Healthy gemini-2.5-provertex_ai/gemini-2.5-proVertex AIChat$1.25 / $10Healthy llama-4-maverickbedrock/llama-4-maverickBedrockChat$0.35 / $1.40Healthy text-embedding-3-largeopenai/text-embedding-3-largeOpenAIEmbedding$0.13 / —Healthy claude-opus-4-8 (global)anthropic/claude-opus-4-1AnthropicChat$5 / $25Degraded Group by: Provider6 providers · 15 models Anthropic — Bedrockclaude-opus-4-8, claude-sonnet-4-5, claude-haiku-4-5bedrock3 Anthropic — Globalclaude-opus-4-8, claude-opus-4-1-20250805global2 OpenAIgpt-5, gpt-5-mini, gpt-5.5-pro, text-embedding-3-largedirect4 Vertex AIgemini-2.5-pro, gemini-2.5-flashgoogle2 Bedrock / Cloudflarellama-4-maverick, mistral-largerouter2 RRoutersprod-router (load-balanced), cheap-fallbackfallback2 + Create TeamShowing 1–7 of 7Org: All TeamMembersModelsKeysSpend / Budget Pplatform-engteam-2f9a…12All8$18.3K / $40K Ddata-scienceteam-71c4…965$6.7K / $12K Aai-gatewayteam-08be…6All4$3.3K / $8K Mml-platformteam-5d20…846$1.9K / $5K Ssupport-aiteam-9a11…433$2.6K / ∞ Ssecurityteam-c7f3…522$0.1K / $0.5K Rresearchteam-3b8d…3All2$0.4K / $2K Pplatform-engteam-2f9a03c1…ActiveEdit Team Spend $18,309 Budget $40,000 Members 12 Keys 8 ModelsAll Proxy Models Rate LimitsTPM 2,000,000·RPM 10,000 Guardrailspii-maskingprompt-injectionsecret-detection Object PermissionsVector Stores · 2MCP Servers · 3 Organizationacme-inc + Add Member7 membersTeam: platform-eng MemberTeam RoleLast Active ARAna Riveraa.rivera@acme.ioAdmin2 min ago JMJae Moraj.mora@acme.ioMember18 min ago SPSam Patels.patel@acme.ioMember1 hr ago KSKir Singhk.singh@acme.ioMember3 hr ago DVDevOps Botdevops@acme.ioAdminjust now CIci-eval-runnerservice accountService7 min ago LCLee Chenl.chen@acme.ioMember5 hr ago Team: AllAccess Group: All6 servers github-mcpSSE https://mcp.acme.io/github 14 toolsplatform jira-mcpSSE https://mcp.acme.io/jira 9 toolsproduct confluence-mcpHTTP https://mcp.acme.io/confluence 6 toolsproduct gitlab-mcpSSE https://mcp.acme.io/gitlab 11 toolsplatform Ssentry-mcpHTTP https://mcp.acme.io/sentry 7 toolssre Sslack-mcpSSE https://mcp.acme.io/slack 5 toolsgeneral ModelsMCPSkillsProvider: All ModelProviderModeContextIn / Out gpt-5OpenAIChat400K$1.25 / $10 claude-opus-4-8AnthropicChat200K$5 / $25 claude-sonnet-4-5AnthropicChat200K$3 / $15 gemini-2.5-proVertex AIChat1M$1.25 / $10 llama-4-maverickBedrockChat128K$0.35 / $1.40 mistral-largeCloudflareChat128K$2 / $6 text-embedding-3-largeOpenAIEmbedding8K$0.13 / — 02 Key PoliciesModel ActivityGuardrailsAudit LogsMonitorRequest Logs Key — Guardrails & Limits Ask AI Export Rate Limits & Budgets TPM Limit2,000,000 RPM Limit10,000 Max Budget$10,000 / month Per-tag budgets: prod $6K · staging $2K · eval $500 Guardrails & Policies Guardrails pii-maskingprompt-injectionsecret-detection Access Groupsprod-gateway, internal-tools Pass-through RoutesAdd /v1/messages, /v1/embeddings Advanced Policies · logging, fallbacks, model aliases CancelSave Settings Range: Last 7 daysTeam: All Teams1.24M requests Requests 1.24M Successful 99.2% Tokens 3.8B Spend $33.9K ModelRequestsTokensSpend gpt-5openai/gpt-5512K1.6B$14.2K claude-opus-4-8anthropic/claude-opus-4-8208K820M$9.8K claude-sonnet-4-5anthropic/claude-sonnet-4-5301K940M$5.1K gemini-2.5-provertex_ai/gemini-2.5-pro142K380M$3.2K llama-4-maverickbedrock/llama-4-maverick77K210M$1.6K + Add Guardrail6 guardrailsMode: All GuardrailProvider / TypeModeStatus Ppresidio-piigr-1a4f…Presidio PIIpre-callActive Llakera-guardgr-77b2…Lakera prompt-injectionduring-callActive Aaporia-policygr-0c31…Aporia moderationpost-callActive Ssecret-detectorgr-9d80…Regex secret-detectionpre-callActive Ttoxicity-filtergr-4e12…LLM Guard toxicitypost-callDisabled prompt-shieldgr-2f56…Bedrock Guardrailspre-callActive Action: AllActor: All7 events today TimestampActorActionObjectChanged By 14:32:07a.rivera@acme.iocreatedkey/acme-prod-gatewayAna Rivera 14:28:51j.mora@acme.ioupdatedteam/data-scienceJae Mora 14:19:03devops@acme.iorotatedkey/ci-eval-runnerDevOps Bot 13:58:44s.patel@acme.iodeletedguardrail/toxicity-filterSam Patel 13:47:12a.rivera@acme.ioupdatedbudget/platform-engAna Rivera 13:21:39k.singh@acme.iocreatedkey/globex-genaiKir Singh 12:55:02devops@acme.ioupdatedmcp/github-mcpDevOps Bot Range: Last 24h84.2K evaluations Evaluations 84.2K Blocked 1,204 Pass Rate 98.6% Avg Latency 42ms Active 5 / 6 GuardrailEvaluationsBlockedPass Rate Ppresidio-pii38.1K40298.9% Llakera-guard21.5K61197.2% Aaporia-policy12.9K9899.2% Ssecret-detector7.4K7199.0% prompt-shield4.3K2299.5% ● LiveStatus: All8 most recent TimeModelKeyStatusLatencyTokensCost 14:32:41gpt-5acme-prod200812ms2,104$0.03 14:32:39claude-opus-4-8wayne-ds2001.2s3,880$0.08 14:32:37claude-sonnet-4-5hooli-data200640ms1,510$0.02 14:32:35gemini-2.5-proglobex-genai42944ms—$0.00 14:32:33gpt-5ci-eval200902ms2,340$0.03 14:32:31llama-4-maverickml-platform200388ms980$0.01 14:32:29mistral-largesupport-ai5005.0s—$0.00 14:32:27claude-sonnet-4-5research200705ms1,220$0.02 Visibility & Control: See every request, and cap it before it runs. See who and what is driving usage and spend, attribute every request for chargeback, and cap budgets before they run. Set budgets and rate limits per team; when they hit the cap, requests stop. Usage and spend tracked per key, user, team, org, tool, agent, and MCP, across 140+ providers. Enterprise chargeback: attribute every request and bill teams and business units for what they use. Hard budgets per key, team, org, and model, with daily and monthly resets. At the cap, requests stop. Rate limits and leaked-key protection, so no runaway job or compromised key runs up your bill. Model access control and guardrails, with an audit log on every request. 03 Cost optimization: Maximize the ROI of your AI. Swap models without changing a line of code, and let Auto Routing send each request to the model that should handle it, so the budget you set goes further. Load balancing across providers, regions, and keys. Lowest-cost routing to the cheapest deployment that can serve the request. Auto Routing that sends simple prompts to cheaper models and hard ones to stronger models. Response and semantic caching (Redis, S3, GCS), so you never pay twice for the same answer. Prompt compression, so you send fewer tokens for the same result. SpendBudgetsTeam SpendScopeDaily Spend Usage — Cost by Team, Key & Model Ask AI Export Range: Last 30 daysOrg: All$48,210.94 total Spend by Team platform-eng$18,309.44 data-science$10,742.15 ai-gateway$6,301.42 ml-platform$5,905.20 Top Virtual Keys wayne-data-science$6,740.15 acme-prod-gateway$4,182.55 hooli-data-squad$3,301.42 globex-genai$1,905.20 Top Models gpt-5$16,884.20 claude-opus-4-8$12,402.55 claude-sonnet-4-5$8,115.90 gemini-2.5-pro$5,340.18 Budget Max Budget$10,000.00 Reset Budgetmonthly Resets on the 1st of each month at 00:00 UTC Budget Windowrolling 30d Soft Limit Alert80% · #ai-platform-ops Fallbacks & Enforcement Budget Fallbacks gpt-5-miniclaude-haiku-4-5 On Budget Exceeded ThrottleBlockFallback Advanced · per-model budgets, tag budgets, reset webhooks CancelSave Settings Range: Year to date7 teams Total Spend $48,210.94 Requests 2,847,103 Successful 2,841,569 Failed 5,534 Tokens 5,912,441,077 TeamRequestsTokensSpendBudget Pplatform-eng1,084,2202.25B$18,309.44$40,000 Ddata-science632,9051.32B$10,742.15$18,000 Aai-gateway371,118770M$6,301.42$10,000 Mml-platform348,004720M$5,905.20$8,000 Ssupport-ai213,441440M$3,618.77$6,000 Rresearch126,510260M$2,152.09$4,000 Ssecurity70,905150M$1,181.87$2,000 PersonalOrganizationTeamTagTeam: All Teams Scope Team Total Spend $48,210.94 Requests 2,847,103 Tags 6 Spend by Tag TagApplied ToRequestsSpend env:prodall teams1,842,004$31,402.18 env:stagingplatform-eng, infra401,552$7,118.44 service:chatsupport-ai, ai-gateway288,110$4,290.05 service:embeddata-science171,904$2,641.60 env:devall teams96,220$1,802.55 service:agentsml-platform, research47,313$956.12 Tag budgets enforced at request time6 of 6 tags Project SpendJul 8 – Jul 15, 2026Range: Last 8 days Total Spend $48,210.94 Max Budget $250,000.00 0809101112131415 Daily spend · all teams, all modelsPeak $8,120.44 on Jul 11 04 Ease of deployment: Go live in your stack in an afternoon Self-host the same open-source gateway behind 240M+ Docker pulls, in your own cloud or fully air-gapped. Simple enough that it just works. Deploy with an official Helm chart or Terraform module Official Docker images, includ

The unified interface for every model. Find the best models & prices for your prompts The Unified Interface For Every Model Better prices, better uptime, no subscriptions. Get API Key Discover Models 400T+ Monthly Tokens 10M+ Global Users 80+ Providers 500+ Models Text, Images, Videos, and Audio Generate anything through a single, unified interface. All major models in one place. Browse all anthropic/claude-opus-5 Higher Availability Reliable AI models via our distributed infrastructure. Fall back to other providers when one goes down. Learn more Price and Performance Keep costs in check without sacrificing speed. OpenRouter runs at the edge for minimal latency between your users and their inference. Learn more Custom Data Policies Protect your organization with fine grained data policies. Ensure prompts only go to the models and providers you trust. View docs Featured Agents 250k+ apps using OpenRouter with 4.2M+ users globally View all Replit The easiest way to go from idea to app Hermes Agent An autonomous agent that grows with you Kilo Code Everything you need for agentic development 1 Signup Create an account to get started. You can set up an org for your team later. 2 Buy credits Credits can be used with any model or provider. Apr 1 $99 Mar 30 $10 3 Get your API key Create an API key and start making requests. Fully OpenAI compatible. OPENROUTER_API_KEY •••••••••••••••• Recent Blog Posts View all Two Hours of Work That Takes a Week For Descript, testing a new model was a couple of hours of work and a week of waiting. The team removed the waiting. Evaluations run in an hour or two now, and nobody has to ask an engineer for time. This post covers the queue, what replaced it, and what changed once evaluation ran several times a week. September 21, 2026 Image Generation Models Compared: Cost, Edit, Quality Image models are priced per token, per megapixel, or per image, so their listed rates do not compare. We sent the same prompt to 20 of them through the Image API, read usage.cost off each response, and tested text rendering, reference-image editing, seeds, and text-plus-image replies. September 18, 2026 Build a Reliable Tool-Calling Agent Loop on OpenRouter A tool-calling agent loop sends the conversation and tool definitions to a model, runs the tool calls the model returns, appends the results, and repeats until the model answers or a stop condition fires. This guide builds that loop in TypeScript with the OpenRouter SDK, then adds an iteration cap, repeated-call detection, model fallback, and history controls. September 17, 2026

One OpenAI-compatible endpoint across providers. Generate an API key, watch your usage, ship. Pay-as-you-go inference — MiMo, Gemini, MiniMax, Qwen · see pricing → open llm inference gateway Opengateway. One endpoint across providers — OpenAI-compatible and Anthropic-compatible. Generate an API key, swap the base URL (or ANTHROPIC_BASE_URL), and ship. Your usage is yours — visible in your console and in a live global view. sign in to generate a key → read the docs → see global usage → checking… curl python node curl https://opengateway.gitlawb.com/v1/chat/completions \ -H "authorization: Bearer ogw_live_…" \ -H "content-type: application/json" \ -d '{ "model": "mimo-v2.5-pro", "messages": [ {"role": "user", "content": "hello, gateway"} ] }' One endpoint, many providers Point any OpenAI-compatible client at opengateway.gitlawb.com/v1 and pass the model. We route to Xiaomi MiMo, Google Gemini, MiniMax, and Qwen — secrets stay server-side. Smart routing with model: “auto” Pass model:“auto” and the gateway picks the cheapest model expected to handle the request, escalating automatically when an upstream fails. Billed at whatever model actually serves. Manage your own keys Generate gateway API keys from your console, scope usage to each one, revoke instantly. No embedded provider secrets in your OSS clients. Real-time usage, yours and global See your own token spend per model, plus the live global gateway view. Built on durable Tigris snapshots — no per-restart resets. smart routingNEW Stop picking models. Send model: “auto”. The gateway inspects each request — estimated context size, tool definitions, code content, reasoning params — and routes it to the cheapest model expected to produce a good answer. When an upstream rate-limits, 5xxs, or returns nothing, it escalates to the next model up the ladder before you ever see an error. You're billed at the rate of the model that actually served, and the x-gateway-served-model response header tells you which one that was. Picks the cheapest model expected to handle the request — scored from context size, tools, code content, and reasoning params Escalates automatically on rate limits, upstream 5xx, and empty responses — up to 3 attempts before you ever see an error Optional route hint: {"priority": "cost" | "balanced" | "quality", "max_cost_usd": 0.01} — stripped before it reaches any provider Billed at the serving model's listed rate — the x-gateway-served-model response header names who answered curl https://opengateway.gitlawb.com/v1/chat/completions \ -H "authorization: Bearer ogw_live_…" \ -H "content-type: application/json" \ -d '{ "model": "auto", "route": {"priority": "cost", "max_cost_usd": 0.01}, "messages": [{"role": "user", "content": "hello, router"}] }' # response header tells you who served it: # x-gateway-served-model: xiaomi/mimo-v2.5 pricing Pay only for what you use. Every model routable through the gateway, priced per token and deducted from your credit balance. Top up with the $10/mo premium plan. modelinput /1Mcached /1Moutput /1M Auto (smart routing)NEW picks the cheapest capable model · escalates on failure model: auto billed at the serving model's rate MiMo V2.5-Pro general large language model model: xiaomi/mimo-v2.5-pro $0.522$0.00432$1.044 MiMo V2.5 multimodal understanding model model: xiaomi/mimo-v2.5 $0.168$0.00336$0.336 Gemini 3.1 Flash Lite low-latency multimodal model · 1M context model: google/gemini-3.1-flash-lite $0.3$0.03$1.8 MiniMax M3 agentic reasoning model model: minimax/minimax-m3 $0.36$0.072$1.44 Qwen 3.7 Max flagship coding model model: qwen/qwen3.7-max $1.5$0.3$4.5 Kimi K3 frontier multimodal reasoning · 1M context model: moonshotai/kimi-k3 $3.6$0.36$18 GLM 5.2 agentic coding & reasoning · 1M context model: z-ai/glm-5.2 $1.68$0.312$5.28 Nemotron 3 Ultra (free)FREE frontier reasoning MoE · 1M context · free (rate limited) model: nvidia/nemotron-3-ultra-550b-a55b:free ⚡ free for everyone — no credits needed $0$0$0 Nemotron 3 Ultra frontier reasoning MoE · 1M context model: nvidia/nemotron-3-ultra-550b-a55b $0.72$0.24$4.32 Ling 3.0 Flash token-efficient agentic MoE · 262k context model: inclusionai/ling-3.0-flash $0.072$0.0144$0.216 Tencent HY3 multimodal model · 262k context model: tencent/hy3 $0.24$0.06$0.96 Macaron V1 Tall routed MoL personal-intelligence model · 262k context model: mindai/macaron-v1-tall $0.54$0.096$3.12 Macaron V1 Venti flagship routed MoL on GLM-5.2 · 1M context model: mindai/macaron-v1-venti $1.8$0.36$5.4 USD per 1M tokens · billed per token from your credit balance · cached input is reused-prompt reads. passing the model id Send the model string exactly as listed above — full provider/model ids (MiMo also accepts the short form mimo-v2.5-pro). Sending auto (or gitlawb/auto) enables smart routing — the x-gateway-served-model response header names the model you were billed for. Per-model capabilities, context windows, and copy-paste snippets live in the model catalog → what you can do A console for your own inference traffic. The gateway already routes traffic for openclaude and the rest of the gitlawb stack. The console is where you manage your own keys and see what you've spent — without leaving a tab to read logs. Use openclaude, opencode, or any OpenAI-compatible client without embedding provider keys Generate a key per project, environment, or teammate — revoke when rotated Watch personal and global token usage update in near real time Pay-as-you-go per token — top up credits and only spend what you use next step Generate your first key. Sign in with Google, X, or an email link, create a key in seconds, top up credits, and start sending requests. Usage is metered per token and billed from your balance. open console → global usage →

OpenCode - The open source coding agent. The open source AI coding agent Free models included or connect any model from any provider, including Claude, GPT, Gemini and more. curl npm bun brew paru yay curl -fsSL https://opencode.ai/v2/install | bash Your browser does not support the video tag. What is OpenCode? OpenCode is an open source agent that helps you write code in your terminal, IDE, or desktop. [*] LSP enabled Automatically loads the right LSPs for the LLM [*] Multi-session Start multiple agents in parallel on the same project [*] Share links Share a link to any session for reference or to debug [*] GitHub Copilot Log in with GitHub to use your Copilot account [*] ChatGPT Plus/Pro Log in with OpenAI to use your ChatGPT Plus or Pro account [*] Any model 75+ LLM providers through Models.dev, including local models [*] Any editor Available as a terminal interface, desktop app, and IDE extension Read docs The open source AI coding agent [*] With over 208,000 GitHub stars, 950 contributors, and over 13,000 commits, OpenCode is used and trusted by over 16M developers every month. Fig 1. 208K GitHub Stars Fig 2. 950 Contributors Fig 3. 16M Monthly Devs Built for privacy first [*] OpenCode does not store any of your code or context data, so that it can operate in privacy sensitive environments. Learn more about privacy. FAQ What is OpenCode? How do I use OpenCode? Do I need extra AI subscriptions to use OpenCode? Can I use my existing AI subscriptions with OpenCode? Can I only use OpenCode in the terminal? How much does OpenCode cost? What about data and privacy? Is OpenCode open source? Access reliable optimized models for coding agents Zen gives you access to a handpicked set of AI models that OpenCode has tested and benchmarked specifically for coding agents. No need to worry about inconsistent performance and quality across providers, use validated models that work. Learn about Zen Be the first to know when we release new products Join the waitlist for early access. ©2026 Anomaly Brand Privacy Terms English

An AI assistant that works for you while you sleep It automates repetitive work for you it automates repetitive tasks it creates concise AI summaries it remembers everything it keeps team follow-ups visible it automates repetitive tasks It automates repetitive work for you it automates repetitive tasks it creates concise AI summaries it remembers everything it keeps team follow-ups visible it automates repetitive tasks Support Support Support Go To Dashboard OPEN BETA Support Support Support It automates repetitive work for you it automates repetitive tasks it creates concise AI summaries it remembers everything it keeps team follow-ups visible it automates repetitive tasks It automates repetitive work for you it automates repetitive tasks it creates concise AI summaries it remembers everything it keeps team follow-ups visible it automates repetitive tasks Support Support Support Go To Dashboard OPEN BETA Support Support Support Powered by Spookling Your AI workspace that thinks with you. Go To Dashboard OPEN BETA Powered by Spookling Your AI workspace that thinks with you. Go To Dashboard OPEN BETA Powered by Spookling Your AI workspace that thinks with you. Go To Dashboard OPEN BETA Task Completed Output optimized Insight Found Key pattern detected Response Generated Ready in 1.2s Context Updated New data applied Model Switched Now using Smart Mode Prompt Improved Clarity +32% Task Completed Output optimized Insight Found Key pattern detected Response Generated Ready in 1.2s Context Updated New data applied Model Switched Now using Smart Mode Prompt Improved Clarity +32% WhatsApp Notion Slack Google Drive GitHub Linear Jira Telegram Airtable Zoom WhatsApp Notion Slack Google Drive GitHub Linear Jira Telegram Airtable Zoom Connect WhatsApp, Gmail, Notion and more. Turn incoming messages into clear tasks. Your AI acts across your everyday tools — without changing how you already work. Connect WhatsApp, Gmail, Notion and more. Turn incoming messages into clear tasks. Your AI acts across your everyday tools — without changing how you already work. Download on the How Spookling Works Start in WhatsApp. Expand everywhere else. AI Summaries That Move Work Forward Text, email, or in-app — ask it to email people, tell people you’re running late, set reminders, or CC it in emails to do work for you. Just tell it what to do, and it does it. It can do anything you need, just ask it! Set jobs for it to do while you sleep Remembers your past conversations AI Summaries That Move Work Forward Text, email, or in-app — ask it to email people, tell people you’re running late, set reminders, or CC it in emails to do work for you. Just tell it what to do, and it does it. It can do anything you need, just ask it! Set jobs for it to do while you sleep Remembers your past conversations It organises your work Spookling connects team messages, tasks, and AI summaries in one workflow, so everyone knows what happened and what to do next. Adds calendar events Edits events in real time Creates PDFs and reports for meetings It turns conversations into tasks It automates repeatable workflows so your team can focus on high-impact work. Easy team context Turns updates into clear actions Can do anything there, just ask it! How Spookling Works Start in WhatsApp. Expand everywhere else. AI Summaries That Move Work Forward Text, email, or in-app — ask it to email people, tell people you’re running late, set reminders, or CC it in emails to do work for you. Just tell it what to do, and it does it. It can do anything you need, just ask it! Set jobs for it to do while you sleep Remembers your past conversations It organises your work Spookling connects team messages, tasks, and AI summaries in one workflow, so everyone knows what happened and what to do next. Adds calendar events Edits events in real time Creates PDFs and reports for meetings It turns conversations into tasks It automates repeatable workflows so your team can focus on high-impact work. Easy team context Turns updates into clear actions Can do anything there, just ask it! Features Features What Your Spookling Can Do 📞 Easy WhatsApp Bot If you receive: "Call the dentist and book me an appointment next week." - Spookling adds to calendar Give it things to do while you sleep. "Research the telecom industry in Panama and draft a business proposal for me for 8am." ✉️ Drafts and sends emails "Email Sarah back and tell her I'm available Tuesday." Video-powered checkout Turn every video into a seamless shopping experience. Attach products directly to your videos in seconds. Make your content interactive and shoppable with zero friction. Smart earnings dashboard Track your revenue, monitor performance, and manage payouts all in one simple view. Video-powered checkout Turn every video into a seamless shopping experience. Attach products directly to your videos in seconds. Make your content interactive and shoppable with zero friction. Smart earnings dashboard Track your revenue, monitor performance, and manage payouts all in one simple view. Download on the Connect Spookling to WhatsApp today Connect Spookling to WhatsApp today Download on the Go To Dashboard OPEN BETA WhatsApp Notion Slack Google Drive GitHub Linear Jira Telegram Airtable Zoom WhatsApp Notion Slack Google Drive GitHub Linear Jira Telegram Airtable Zoom Search Locally Works natively on iOS Turn team messages into tasks Summarises project updates for you Task Automation AI Summaries for Important Updates Search Locally Locally Filtered AI Summaries Built for Team Conversations Collaborative Messaging AI Summaries for Important Updates Set and track team follow-ups Summarise updates and next steps Respond to your coworkers Search Locally Locally Filtered Task Automation AI Summaries for Important Updates AI Summaries Search Locally Built for Team Conversations Locally Filtered Collaborative Messaging Search Locally Add events to your calendar Organize your inbox Negotiate deals for you Summarize long documents AI Summaries for Important Updates Search Locally Locally Filtered Collaborative Messaging Built for Team Conversations Task Automation AI Summaries for Important Updates From the blog From the blog Ideas on automation, AI summaries, and team collaboration Ideas on automation, AI summaries, and team collaboration View All Feb 19, 2026 Turning Repetitive Work Into Clear Next Steps Read More Feb 19, 2026 Turning Repetitive Work Into Clear Next Steps Read More Feb 19, 2026 Turning Repetitive Work Into Clear Next Steps Read More Feb 19, 2026 From Team Conversations to Actionable Work Read More Feb 19, 2026 From Team Conversations to Actionable Work Read More Feb 19, 2026 From Team Conversations to Actionable Work Read More Feb 19, 2026 Making Space for Better Team Decisions Read More Feb 19, 2026 Making Space for Better Team Decisions Read More Feb 19, 2026 Making Space for Better Team Decisions Read More Feb 19, 2026 AI Summaries That Keep Work Moving Read More Feb 19, 2026 AI Summaries That Keep Work Moving Read More Feb 19, 2026 AI Summaries That Keep Work Moving Read More FAQs FAQs Common questions about Spookling Common questions about Spookling Categories General Workflow Features Team & Trust What is Spookling? Spookling brings task automation, AI summaries, and collaborative team messaging into one focused workspace. What can Spookling automate? Spookling helps automate repetitive work, organise follow-ups, and turn everyday team activity into clear next steps. Can Spookling turn a conversation into a task? Yes. When a conversation creates an action, Spookling can help capture it as a task instead of leaving it buried in chat. Does Spookling understand the context of a task? Spookling keeps the surrounding conversation and task context together, helping people act on the right information. How is Spookling different from a chatbot? A chatbot mainly responds with text. Spookling is focused on helping people move from conversation to organised work. Still have a question? If you didn't find your answer, feel free to reach out. Contact Us Categories General Workflow Features Team & Trust What is Spookling? Spookling brings task automation, AI summaries, and collaborative team messaging into one focused workspace. What can Spookling automate? Spookling helps automate repetitive work, organise follow-ups, and turn everyday team activity into clear next steps. Can Spookling turn a conversation into a task? Yes. When a conversation creates an action, Spookling can help capture it as a task instead of leaving it buried in chat. Does Spookling understand the context of a task? Spookling keeps the surrounding conversation and task context together, helping people act on the right information. How is Spookling different from a chatbot? A chatbot mainly responds with text. Spookling is focused on helping people move from conversation to organised work. Still have a question? If you didn't find your answer, feel free to reach out. Contact Us Categories General Workflow Features Team & Trust What is Spookling? Spookling brings task automation, AI summaries, and collaborative team messaging into one focused workspace. What can Spookling automate? Spookling helps automate repetitive work, organise follow-ups, and turn everyday team activity into clear next steps. Can Spookling turn a conversation into a task? Yes. When a conversation creates an action, Spookling can help capture it as a task instead of leaving it buried in chat. Does Spookling understand the context of a task? Spookling keeps the surrounding conversation and task context together, helping people act on the right information. How is Spookling different from a chatbot? A chatbot mainly responds with text. Spookling is focused on helping people move from conversation to organised work. Still have a question? If you didn't find your answer, feel free to reach out. Contact Us Meet your Spookling. The workflows that move work forward The workflows that move work forward Download on the Go To Dashboard OPEN BETA WhatsApp Notion Slack Google Drive GitHub Linear Jira Telegram Airtable Zoom WhatsApp Notion Slack Google Drive GitHub Linear Jira Telegram Airtable Zoom Terms of Service Privacy Policy © 2026 Spookling © 2026 Spookling © 2026 Spookling