Work Here?
Overview
OpenRouter provides a single OpenAI-compatible API to access and switch between 400+ models from 60+ providers. It acts as an LLM router and aggregator, directing prompts to the best model based on price, latency, and performance with about 25ms of overhead. The platform offers unified billing, real-time spend management, automatic failover, and enterprise features like zero-logging and using a company’s own provider keys, earning 5% of inference costs. Its goal is to simplify the fragmented AI model ecosystem by enabling dependable multi-model access and transparent usage data.
About OpenRouter
Industries
Data & Analytics
Enterprise Software
AI & Machine Learning
Company Size
51-200
Company Stage
Acquired
Total Funding
$153M
Headquarters
New York City, New York
Founded
2023
Get referred to OpenRouter
See people who can refer or advise you
Simplify's Take
What believers are saying
- Weekly token volume exploded from 5T to 25T in six months, reflecting enterprise shift from single-model pilots to production-grade multi-model systems.
- May 2026 release added voice/speech APIs and Model Fusion, closing the last modality gap for creators needing unified text/image/audio/voice access.
- Secured $113M Series B in May 2026 led by CapitalG, valuing the company at $1.3B, as strategic investors signal convergence on multi-model routing.
What critics are saying
- Ofox AI eliminates OpenRouter’s 5.5% credit fee and includes public SLA, undercutting pricing for $1M+/mo enterprise spenders in 9–12 months with high impact.
- LiteLLM’s self-hosted model removes all fees and adds ~$20–50/mo server cost, becoming cheaper at scale for engineering teams with VPS in 6–12 months.
- Open-source, self-hosted alternatives enable non-US developers to bypass US export controls and geopolitical interference, threatening OpenRouter’s risk model in 18–36 months.
What makes OpenRouter unique
- OpenRouter’s Fusion API delivers near-Claude Fable 5 intelligence at half the cost via judge-synthesizer pipeline fusing budget models.
- Its MCP server gives coding agents live model benchmarks, pricing, and test inference, eliminating 15+ minutes of manual tab-switching before integration.
- Bittensor’s Chutes subnet routes 20–25% of 100–120B daily tokens through OpenRouter, validating decentralized TEE-based confidential inference as commercially competitive.
Help us improve and share your feedback! Did you find this helpful?
Funding
Total Funding
$153M
Above
Industry Average
Funded Over
4 Rounds
Andreessen Horowitz
Menlo VenturesBenefits
Remote Work Options
Flexible Work Hours
Unlimited Paid Time Off
Growth & Insights and Company News
6 month growth
↑ 27%1 year growth
↑ 27%2 year growth
↑ 50%OpenRouter integrates speech transcription into the same API: one key to handle chatting and transcription. Whisper and token-based STT are both integrated. Published in Latest AI News Time: Jul 22, 2026 Read: 10minute Developers working on speech transcription have long been troubled by a sense of fragmentation: chat with OpenRouter, but transcribe with another Whisper server, or integrate with a third-party SDK for audio-to-text. On July 22, OpenRouter smoothed this gap - it launched the POST /api/v1/audio/transcriptions endpoint on its platform, allowing users to send base64-encoded audio with the same Bearer key used for Chat Completions and receive a JSON response containing the transcribed text and usage details. Chat and transcription now share one ticket. The core of this convenience is reuse. You don't need a new SDK or separate service, as the transcription feature runs on the same platform as chat traffic, with models from multiple providers automatically load balancing between each other rather than being locked into a single vendor. For teams that already use OpenRouter as their main platform, this integration means fewer maintenance steps and fewer keys to remember. On the model side, OpenRouter offers two approaches. One is Whisper-like models such as openai/whisper-1, billed by audio duration, i.e., per second; the other is newer speech-to-text (STT) models, billed by tokens. It's worth noting that STT model IDs won't appear in the default /api/v1/models directory, as they belong to an output modality requiring active filtering - through the ?output_modalities=transcription parameter, you can filter out these models and their current pricing. If you want to try before integrating, the OpenRouter Playground also allows direct file upload and transcription within the browser. The call method is simple enough to close the loop in one request. Encode the file in base64, POST it along with the model and format, then read the text and usage fields from the response. The data field takes raw base64 bytes, not a data: URI, so don't add the data:audio/mp3;base64 prefix; the format field is required to tell the upstream model how to decode these bytes. If you already have a client written for OpenAI's /v1/audio/transcriptions, simply point the base URL to https://openrouter.ai/api/v1 to use it directly with zero changes. The endpoint also accepts OpenAI-style multipart/form-data uploads, with files and models, up to a 25MB limit. Regarding field specifications, model, input_audio.data, and input_audio.format are required fields. The format can be one of wav, mp3, flac, m4a, ogg, webm, or aac; language is an ISO-639-1 language code, which will be detected automatically if omitted; temperature controls sampling, with values ranging from 0 to 1; response_format defaults to json, and setting it to verbose_json gives additional information about the task, language, duration, and segment timestamps. With timestamp_granularities set to word, you can even get word-level timestamps. However, these features are only available on providers compatible with OpenAI, such as OpenAI, Groq, and Together, while other providers will return a 400 error directly. The provider block is used to pass through each provider's private parameters, for example, Groq can pass expected vocabulary via provider.options.groq.prompt to help the model correctly handle proper nouns, avoiding mispronouncing technical terms. The response is a JSON object, with the text string containing the transcription result, and the usage object allowing costs to be measured by request rather than estimated. In an example, a 9.2-second audio produced 113 tokens, 83 inputs, and 30 outputs, with a cost of $0.000508 - this number comes from the document example, not an actual quote, and the real cost depends on the selected model and audio length. The response header also includes an X-Generation-Id, which helps you record and track a specific request. The routing logic follows the same system as chat. When a transcription model is hosted by multiple providers, OpenRouter performs load balancing based on price, distributing requests among them to avoid being tied to a single vendor. However, the transcription endpoint currently does not support route control per request. Fields like order, only, allow_fallbacks, data_collection, and sort, familiar in chat calls, do not work here. The provider block only carries provider-specific options. OpenRouter explicitly does not mark up provider pricing, and the listed price is your actual payment price. The zero-fallback insurance means that failed transcriptions will not be charged; if you have your own provider agreement, the BYOK feature allows using your own keys for routing, paying only the platform fee and eliminating the variable model cost. Additionally, the platform fee for the first 1 million requests per month is waived under the variable billing model. Before actually building, there are four constraints that must be considered in the architecture. First, a 60-second upstream timeout - this refers to processing time, not audio length, so large or uncompressed recordings may time out; long audio should be split into segments and the text concatenated. Second, audio URLs are not supported; the endpoint only accepts base64 JSON or OpenAI-style multipart files not exceeding 25MB. Third, SRT/VTT format outputs are not supported; srt, vtt, and text will be rejected with a 400 error, and timestamps can only be obtained via verbose_json, with subtitles needing to be manually assembled using timestamps. Fourth, format support varies by provider, with wav being the most compatible safe default, while compressed formats like mp3 can generate smaller and faster payloads. A recording lasting several hours, like a night-long gaming session, cannot be handled in a single call and must be processed in chunks. Finally, putting transcription in the right place. When you just need to convert audio into text, use /audio/transcriptions; when you want the model to reason about the audio content, such as sentiment analysis of customer service calls, answering questions about audio, or combining audio with other modalities in the same prompt, use the input_audio content type in /chat/completions. Text-to-speech is a third independent endpoint. OpenRouter's comparison is straightforward: for a transcription, go to the transcription endpoint to get JSON text and usage; for a model that understands audio, go to chat completion to get a single conversation result. With one key covering both conversations and sound, the barrier for implementing voice capabilities in applications has been quietly lowered again.
OpenRouter deal valuation highlights AI infra shift. By Adam Pease Fintech vendors increasingly seek growth beyond traditional payment processing as artificial intelligence infrastructure becomes central to digital commerce. Recent reports indicate that Stripe is in advanced discussions to acquire OpenRouter in a deal that could value the startup near ten billion dollars. The startup operates an infrastructure marketplace that routes developer traffic across hundreds of proprietary and open-weight models. This blog overviews the Stripe acquisition talks with OpenRouter and offers its analysis. Why is Stripe targeting OpenRouter? OpenRouter provides developers with a unified entry point to access, compare, and switch between multiple artificial intelligence models through a single API. By abstracting model integration complexities and managing dynamic request routing based on cost, latency, and capability, the platform occupies a critical position in the modern software stack. Stripe already maintains an operational connection with the vendor, powering its underlying billing, tax, and invoicing functions. Acquiring this business allows Stripe to move directly into the monetization and metering layer of the artificial intelligence ecosystem, capturing transaction flow directly at the gateway level. Analysis. This potential transaction represents a strategic pivot for both enterprise software and financial technology infrastructure. For Stripe, acquiring OpenRouter is not simply an expansion of payment services, but a deliberate move to control the enterprise inference control plane. By owning the gateway where enterprises select and route queries across models, Stripe positions itself to control usage metering, dynamic pricing, and micro-settlements across distinct model providers. This consolidation forces competing payment processors to rethink how they will support usage-based API billing in multi-model environments. Model aggregation and routing gateways are becoming primary governance points. Independent model providers face potential disintermediation if access layer ownership shifts to payment platforms. Competitors in the ecosystem will likely feel compelled to build or acquire similar routing capabilities to maintain direct customer billing relationships. What enterprises should do. Enterprises should closely monitor this development and evaluate their multi-model artificial intelligence deployment strategies. Reliance on third-party routing gateways requires assessing potential vendor lock-in, data privacy protocols, and API longevity. Enterprise technology leaders must evaluate how API metering and model switching costs affect overall infrastructure budgets. Preparing for usage-based billing mechanisms across enterprise deployments will become essential as technology consolidation continues. Bottom line. The potential acquisition of OpenRouter by Stripe highlights the convergence of financial settlement layers and artificial intelligence routing infrastructure. Organizations must evaluate their gateway dependencies and prepare for integrated API metering across their technology stack.
The OpenRouter MCP server. OpenRouter ·6/25/2026 Your coding agent is incredible at writing code. But when it comes to choosing the right model for, say, coding without blowing through your monthly budget in one day, or the best model for designing a landing page, it really struggles. Your agent can make an approximate guess of the "best" model, but it's guessing from training data that is months stale, with no knowledge of how much it costs, how well it performs for a given task, which provider you should pin it to, etc. Today, OpenRouter, LLC is very excited to announce the release of the OpenRouter MCP. The OpenRouter MCP server puts live model data, benchmark rankings, pricing, docs, and test inference directly to help you and your agent to make the right decisions on the best model to use. Install in one command, and your favorite agent can answer "which model is the best at coding without bankrupting me" with the most up-to-date data Artificial Analysis, Design Arena, and OpenRouter's own model rankings. Hint: it's GLM-5.2. Install in one command. Claude Code: claude mcp add -transport http openrouter https://mcp.openrouter.ai/mcp claude mcp login openrouter Codex CLI: codex mcp add openrouter -url https://mcp.openrouter.ai/mcp codex mcp login openrouter Cursor: Add to ~/.cursor/mcp.json: { "mcpServers": {"openrouter": { "url": "https://mcp.openrouter.ai/mcp"}}} Claude Desktop / Web: OpenRouter isn't in Claude's connector directory, so add it yourself: Settings > Connectors > Customize > Connectors, click the + > Add custom connector, enter the name OpenRouter MCP and the Remote MCP server URL https://mcp.openrouter.ai/mcp, click Add, then open the connector and Connect to run the OAuth flow. Some organizations don't allow adding custom connectors, so this option may not show up for everyone. Talk to your admin if that's the case. See the connect guide for OAuth login and every supported client. Pick the right model without tab-switching. You're building a feature that needs structured JSON output, and you want a model that's fast, cheap, and actually good at it. Normally you'd open the OpenRouter website, browse the model list, compare benchmarks, check pricing, maybe run a few test prompts in the playground. That's 15 minutes of context-switching before you write a single line of integration code. With the MCP server connected, you can do this all in your coding agent: You: "I need a model for structured JSON extraction from legal documents. Fast, under $1/M input tokens, good at following schemas." Agent: [calls models-list with filters] | [calls benchmarks] | [calls model-endpoints] Agent: "google/gemini-3-flash-preview fits well: $0.10/M input, 138k context, strong structured output support. Here's the endpoint with the lowest latency..." The agent pulls from the live model catalog, cross-references Artificial Analysis intelligence scores and Design Arena ELO rankings, and checks per-provider pricing and latency. The recommendation is fully grounded in current data, not whatever was true when the model was last trained 6 months ago. Test before you commit. chat-send lets your agent fire off a test prompt to any model and see the response, cost, and which provider served it. Your agent can compare answers across models side-by-side: You: "Compare how Claude Opus 4.8, GPT-5.5, and DeepSeek V4 Pro handle this structured extraction prompt." Agent: [sends the same prompt to all three via chat-send] [calls generation-get for each to get cost breakdowns] Agent: "All three produced valid JSON. Opus 4.8 nailed the edge case in row 12. GPT-5.5 was 40% cheaper. DeepSeek V4 Pro was fastest at 180ms TTFB." Model slugs support suffixes: :online for web search, :nitro for speed, :floor for the lowest price, :free for free endpoints. Your agent can test across variants without you memorizing the syntax. Search the docs without leaving your editor. Your agent has docs-search, which runs a full-text search across the OpenRouter documentation. "How do I pin a model to a specific provider?" "What's the format for tool calling?" "How does prompt caching work?" Your agent finds the answer and applies it, all in one flow. This is where the MCP server earns its keep as a development assistant. Your agent can look up the exact API parameter it needs, check the right request format, and wire it into your code without you having to find and read the docs page yourself. A dedicated, capped key. The server is remote (nothing installed locally), and the first login runs an OAuth flow that mints a dedicated API key with a 7-day expiry and a $10 spend cap (editable on the approval screen). It's separate from your other keys and shows up on your keys dashboard. You can revoke it any time. See the connect guide for setup in OpenCode, Claude Desktop, and every other supported client. What's in the toolbox. | Tool | What it does | | models-list | Search the live model catalog with filters: price range, context length, modality, provider, model family, and more | | model-get | Full details for one model: capabilities, pricing, context window, supported parameters | | model-endpoints | Per-provider breakdown: price, latency, throughput, data policy | | benchmarks | Third-party quality scores from Artificial Analysis and Design Arena | | rankings-daily | Which models are most used and trending by token volume | | chat-send | Send a test prompt to any model, get the response and cost | | generation-get | Cost, token counts, and serving provider for a specific generation | | docs-search | Full-text search across OpenRouter docs | | credits-get | Your remaining account credit | | providers-list | Available providers for routing preferences | | app-rankings | Which apps drive the most OpenRouter traffic, by category | All tools except chat-send are read-only lookups. chat-send makes a billable inference call using your MCP key's balance. Faq. Does this replace the OpenRouter API? No. The MCP server is a development assistant for your coding agent. It pulls live OpenRouter data and can send test messages so your agent makes informed decisions while you build. Your app should still call the OpenRouter API directly. How does authentication work? Your MCP client triggers an OAuth flow that opens an OpenRouter consent page in your browser. You approve a dedicated API key with a 7-day expiry and a $10 spend cap. The key is separate from your other keys and can be disconnected anytime from your dashboard. Does my source code get sent anywhere? No. The tools are read-only lookups against the OpenRouter API. The only exception is chat-send, which sends the message you explicitly pass to it to a model. No source code leaves your machine unless you include it in a chat-send call. Try it now: connect your agent and ask "what's the best model for my use case?"
OpenRouter raises $113M Series B. OpenRouter · 5/28/2026 Today OpenRouter, LLC is announcing its $113M Series B, led by CapitalG (Alphabet's independent growth fund), with participation from NVentures (NVIDIA's venture capital arm), ServiceNow Ventures, MongoDB Ventures, Snowflake Ventures, Databricks Ventures, AMP PBC, and Pace Capital, alongside its existing investors Andreessen Horowitz and Menlo Ventures. Where OpenRouter, LLC is. Over the last six months, weekly volume on OpenRouter has grown from 5 trillion to 25 trillion tokens. OpenRouter, LLC is on pace to process over a quadrillion tokens this year and serve 8M+ developers building across 400+ models. AI is rapidly shifting from experimentation into critical production apps and agents, and that transition requires infrastructure that works reliably at scale, across providers, across modalities, and across use cases. This growth reflects the simple fact that developers love building on OpenRouter. Why this round matters. The composition of this investor group is deliberate. CapitalG, NVentures, ServiceNow Ventures, MongoDB Ventures, Snowflake Ventures, and Databricks Ventures are more than financial backers; they are the infrastructure and platform companies that enterprises already depend on. Their participation reflects a shared view: as organizations move from single-model pilots to multi-model production systems, they need a routing and gateway layer purpose-built for that complexity. OpenRouter is that layer. OpenRouter, LLC sit between agents and model providers, handling the routing, reliability, cost optimization, and compliance that production AI demands. The breadth of strategic investors in this round signals that the market has converged on this as a critical piece of the stack. What OpenRouter, LLC has been building. The past year has been focused on expanding what OpenRouter can do for production workloads: * Multimodal inference: Beyond text, OpenRouter now supports image, audio, speech, transcription, embedding, and video models. * Enterprise controls: Workspaces, spend management, guardrails, and zero-data-retention policies for organizations deploying AI at scale. * Intelligent routing: Provider-level failover, cost and latency optimization, and quality-aware routing that goes beyond simple load balancing. What's next. OpenRouter, LLC'll use this funding to continue scaling its infrastructure, deepen enterprise capabilities, and continue to invest in intelligent routing; teams need help finding the right model and provider for every request. OpenRouter, LLC is grateful to its customers, partners, investors, and the developer community building with OpenRouter, LLC as OpenRouter, LLC continue scaling the infrastructure layer for the multi-model AI era.
How did GateRouter become one of the most user-friendly AI tools in the crypto industry? Updated: 2026-04-09 21:44 The following is an AI-generated summary of this article. Main Topic GateRouter is an AI model aggregation platform for the crypto industry that solves integration challenges for developers through a unified API, intelligent routing, and Web3-native payment. Key Points * Smart routing automatically assigns models based on task complexity, with the cost Over the past year, developers in the crypto industry have faced an awkward dilemma: leading AI models like OpenAI, Claude, Gemini, and DeepSeek each have their strengths, but integrating a full suite of AI capabilities means juggling multiple API keys, adapting to wildly different billing structures, and dealing with inconsistent response speeds. For a typical DeFi protocol aiming to connect with three or four models for cross-validation, development costs often add up by the month. GateRouter's core value lies in eliminating this "integration pain." It's not a new AI model, but rather an intelligent parsing and orchestration layer that sits between client applications and top global model providers. Developers only need to connect to a unified API to access all integrated models, freeing them from low-level integration work and allowing them to focus on innovation at the application layer. Intelligent routing: maximizing every dollar spent. For professionals in the crypto sector, cost control is always a priority. Whether it's a high-frequency quantitative strategy system or a 24/7 on-chain monitoring bot, inference costs often directly determine a project's economic viability. GateRouter's intelligent routing mechanism was designed for this very purpose. The system automatically assigns the most suitable model based on task complexity. Simple greeting tasks are matched with lightweight models, consuming only 7.1% of the tokens compared to a direct GPT-4 call - reducing costs by 92.9%. For complex tasks, such as risk assessments of 5,000-word legal contracts, the system matches high-performance flagship models, with actual expenses at just 20% of a direct call. Overall, compared to using flagship models exclusively, GateRouter can reduce average AI inference costs by over 80%. Users have tested three scenarios - daily greetings, code generation, and complex document summarization - and found results closely aligned with official data. The precision of intelligent routing is impressive. In high-frequency usage scenarios, this cost optimization translates into visibly higher profit margins. Web3 native payments: giving AI agents a true "wallet" While unified APIs and intelligent routing boost efficiency, GateRouter's payment mechanism fundamentally transforms industry paradigms - this is its key distinction from Web2 competitors like OpenRouter. Traditionally, API calls rely on credit cards or prepaid accounts, essentially a "human-centric" payment logic. GateRouter natively integrates the x402 payment protocol and supports direct USDT deductions via Gate Pay. This means AI agents can, for the first time, have their own "crypto wallets" and make autonomous payments. Imagine a future where a decentralized automated trading agent spots an arbitrage opportunity while monitoring the market. It sends a request to GateRouter, which returns a payment requirement. The agent automatically pays USDT from its crypto wallet, then receives model feedback and executes an on-chain transaction. This machine-to-machine payment scenario is the foundation of the future "Agent Economy." By embedding the payment layer into API calls, GateRouter enables AI to independently participate in crypto economic activity - not just serve as a tool in human hands. Developer-Friendly: from console to privacy protection. Beyond its core capabilities, GateRouter also excels in developer experience. The platform offers a comprehensive developer console, allowing clear visibility into each call's model assignment, token consumption, and response time - providing data to optimize application performance. The built-in Playground feature lets developers quickly switch between models, compare outputs and cost differences for the same prompt across models. On the data security front, GateRouter does not store user conversation content by default, and all data transmission is encrypted via HTTPS. The platform follows a "privacy-first" design philosophy. While optional logging is available, it requires manual activation by developers and supports log deletion at any time. This is especially critical for developers handling sensitive on-chain data. Conclusion. In 2026, as AI and blockchain become deeply intertwined, GateRouter's "unified API + intelligent routing + Web3 native payments" triad architecture precisely addresses the core pain points of crypto professionals. With a single line of code and a 30-second integration, it dramatically lowers the barrier to AI development. Intelligent routing reduces inference costs by over 80% on average, making high-frequency AI usage economically viable. Crypto-native payments open the door for AI agents to autonomously engage in economic activities, allowing machines to complete the full cycle of thinking, payment, and execution independently. For crypto developers, quantitative trading teams, and AI agent builders, GateRouter is more than just an AI tool - it's the foundational infrastructure for the next-generation Agent Economy. Whether you're a professional team building smart trading systems or an individual developer just starting out, GateRouter empowers you to seize opportunities in the AI-driven crypto wave with lower costs and higher efficiency. As of April 2026, GateRouter continues to expand its model ecosystem, with official plans to integrate over 50 models within the year. The future is here - why not start with a simple API call? The content herein does not constitute any offer, solicitation, or recommendation. You should always seek independent professional advice before making any investment decisions. Please note that Gate may restrict or prohibit the use of all or a portion of the Services from Restricted Locations. For more information, please read the User Agreement Like the Content
OpenRouter is Hiring for 18 Jobs on Simplify!
Find jobs on Simplify and start your career today
About OpenRouter
Industries
Data & Analytics
Enterprise Software
AI & Machine Learning
Company Size
51-200
Company Stage
Acquired
Total Funding
$153M
Headquarters
New York City, New York
Founded
2023
OpenRouter is Hiring for 18 Jobs on Simplify!
Find jobs on Simplify and start your career today