How does OpenRouter pricing work?

You buy credits that work across any model or provider, instead of holding a subscription with each vendor. Per-token prices vary by model and are shown alongside each one.

Do I need to change my code to use it?

The API is OpenAI-compatible, so most integrations work by changing the base URL and key. Switching models is then a string change rather than a rewrite.

What happens if a provider goes down?

Requests fall back to another provider serving the same model automatically, which is the main reason teams route through OpenRouter rather than calling vendors directly.

OpenRouter News

ElevenLabs is now on OpenRouter

October 7, 2026

ElevenLabs is now on OpenRouter with 9 Text to Speech and 2 Speech to Text models. Deliver speech with human-like emotion with Eleven v4, give your agent low-latency replies with v4 Turbo, and turn meetings into notes that show who said what with Scribe v2. Here's which model to pick, and one project built start to finish.

Model Router Benchmarks

October 2, 2026

We now benchmark model routers side by side across six suites. Our Router Index weighs quality, speed, and cost so you can decide if you need a router and pick the best one for your needs.

Manage and de-risk your API keys with new Security Center

September 28, 2026

We audited our own OpenRouter account and found over 1,000 active API keys for 85 employees, 168 of them hadn't been used in months. The new Security Center helps you manage and de-risk your API keys with one place to see every key, know which ones are risky and why, clean them up, and lock them to your own network.

Batch API: half-price inference by bundling requests

September 22, 2026

Send a whole workload in one POST, collect the results within 24 hours, and typically pay half the per-token price. Across 230k+ batches that completed over our two week beta period, the median finished in 7 minutes.

In-Region Routing: Keep your data in the US or EU

September 9, 2026

US In-Region Routing is live, joining the EU. Send requests to us.openrouter.ai and they are decrypted only inside the United States and served only by providers running there, across models from OpenAI, Anthropic, Google, NVIDIA, Thinking Machines, DeepSeek, Moonshot, and Qwen.

Give any model a terminal and files

September 8, 2026

The shell server tool gives any model on OpenRouter a hosted Linux shell, and the Files API moves files in and out of it. Commands run in an isolated container, the model reads back stdout, stderr, and exit codes, and files the run writes can be downloaded afterward. Available today in beta on the Responses and Messages APIs.

Image Benchmarks: See the Capabilities of Every Model

August 21, 2026

We ran 39 image models through 15 deliberately hard prompts and put every result on one page. Compare fill levels, finger counts, poster text, and edits side by side, with the price and generation time under each image.

OpenRouter is Joining Stripe

August 19, 2026

Today, we are excited to announce that we are joining forces with Stripe, to power the next wave of GDP growth globally.

Understand your AI usage: every agent, model, and request

August 17, 2026

See what your team spent on every model, save the charts you keep rebuilding, click any bar to land in the logs behind it, and query the same data from your terminal with the Analytics API.

Stripe to Acquire OpenRouter for Over $7 Billion

August 16, 2026

via Stripe

Bloomberg reports Stripe has agreed to buy OpenRouter, the AI model-routing startup, for more than $7 billion — one of its largest acquisitions and a push past payments into AI infrastructure. OpenRouter routes 200 trillion tokens a month for 10M+ users across 500+ models and 80+ providers, and already runs its own billing on Stripe. The price is roughly 5.4x the $1.3 billion valuation it raised at three months earlier. Stripe has declined to comment on the report.