← OpenRouter pricing
What we read
This is the text we read from https://openrouter.ai/pricing at 2026-08-21 07:12 UTC. Every figure in our OpenRouter pricing guide was extracted from it.
Gemini 3.7 Flash is 75% off for a limited time. See all discounted models here (opens in new tab) Dismiss Skip to content Search ⌘ K Models Benchmarks Chat Rankings Apps Enterprise Docs Sign Up Pricing Plans for indie hackers, AI native startups, and enterprises Get Started Talk To Sales Free Pay-as-you-go Enterprise Platform Fees N/A 5.5% Fee discounts available Models Explore all models → 25+ free models 500+ models 500+ models Providers Explore all models → 4 free providers 80+ providers 80+ providers Chat and API Access Try chat now → Activity Logs & Export Auto-routing, preferred vendor selections Learn more → Budgets & Spend Controls Prompt Caching Learn more → Management API key Learn more → Admin Controls Enterprise features → Data Policy-Based Routing Model & provider policies Managed Policy Enforcement SSO/SAML Contractual SLAs Payment options Credit card, crypto & more Invoicing options BYOK Limits Learn more → $25,000 of list price inference / month with no fees, 5% fee after $200,000 of list price inference / month with no fees, 5% fee after Rate limits 50 reqs/day High global limits Optional dedicated limits Token Pricing Free models only No minimum spend. Prices based on models Volume commitments. Prices based on models Support Community Support Email Support Support SLA with Shared Slack Channel Get Started For Free Buy Credits Contact Sales Frequently Asked Questions Billing and Pricing How are tokens billed? Do you mark up provider pricing? How is billing structured for BYOK, Pay‑As‑You‑Go vs Enterprise? Are failed or fallback attempts billed? Do you offer volume discounts or annual plans? Are streaming responses billed differently? What payment methods do you accept? Are taxes (VAT/GST) included in prices? Is there a minimum spend or lock‑in on Pay-as-you-go ? Usage and Rate Limits Do you enforce rate limits? Can I separate environments (dev/staging/production)? Do you enforce platform rate limits? Routing and Latency Can I make sure to send API requests in specific regions? Does routing affect latency? What happens if a model is deprecated or pricing changes? Can I pin specific model versions? Privacy and Security Do you train on customer data? Do you support SSO? Models and Features How do I migrate from OpenAI/Anthropic? Do you support function calling/tools? Reliability and Uptime What happens if a provider is down or a model errors? Where can I check uptime and incidents? Ready To Get Started? Join thousands of developers building with OpenRouter Sign Up For Free Contact Sales © 2026 OpenRouter, Inc Product Chat Rankings Benchmarks Apps Discover Models Collections Providers Pricing Enterprise Labs Company About Blog Careers Hiring Privacy Terms of Service Support Works With OR Data Developer Documentation API Reference Developer Platform Status Connect Discord GitHub LinkedIn X YouTube Cookie Preferences We use essential cookies for site functionality and optional cookies for analytics. Privacy policy Decline Accept
STRUCTURED PRICING DATA:
{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"How are tokens billed?","acceptedAnswer":{"@type":"Answer","text":"Input and output tokens are billed per model at posted rates."}},{"@type":"Question","name":"Do you mark up provider pricing?","acceptedAnswer":{"@type":"Answer","text":"We do not mark up provider pricing. Pricing shown in the model catalog is what you pay which is exactly what you will see on provider's websites."}},{"@type":"Question","name":"How is billing structured for BYOK, Pay‑As‑You‑Go vs Enterprise?","acceptedAnswer":{"@type":"Answer","text":"Pay-as-you-go: You buy credits and use them as you wish. You can automatically top-up your account or do it manually. You can see the activity in your settings > API Keys Enterprise: Pricing is based on volume, prepayment credits, annual commits, and many other factors."}},{"@type":"Question","name":"Are failed or fallback attempts billed?","acceptedAnswer":{"@t