FAQ

OneRouter is a unified AI API gateway that gives you a single OpenAI-compatible endpoint to access 200+ models from 50+ providers — including OpenAI, Anthropic, Google, Meta, DeepSeek, and more.

Here's how it works: you send requests to OneRouter's API in standard OpenAI format. OneRouter routes your request to the appropriate upstream provider, translates the format if needed, handles the response, and returns it to you. From your perspective, you call one API — OneRouter manages model routing, load balancing, rate limiting, automatic failover, and cost tracking behind the scenes.

You only need a OneRouter account. We handle all upstream provider relationships on your behalf — no separate accounts with OpenAI, Anthropic, or Google required.

• One key, every model — Access GPT-4o, Claude Opus, Gemini Pro, and DeepSeek V3 with a single API key. No managing multiple billing accounts across different providers.
• No vendor lock-in — Switch models by changing one parameter. Your code stays the same regardless of which provider serves the request.
• Automatic failover — If a provider goes down, traffic auto-routes to your backup model. Zero manual intervention.
• Global access — No regional restrictions. Developers worldwide access frontier models without geo-blocks.
• Cost visibility — Unified billing and real-time usage tracking across every model and provider in one dashboard.

Getting started takes about 5 minutes:

1. Sign up at api.onerouter.app/register
2. Add credits to your account via credit card, PayPal, or crypto
3. Create an API key from the Dashboard → API Keys page
4. Make your first call — just change base_url to https://api.onerouter.app/v1 and use your new key

If you already use the OpenAI SDK, you're 30 seconds away. See the Quickstart guide for code examples in Python, TypeScript, and curl.

We don't offer a permanent free tier — here's why that's actually good for you:

• No subsidized quality degradation — Free tiers at scale require cutting corners on infrastructure, support, or model access. We invest everything into reliability and model coverage.
• Pay only for what you use — No minimum commitment. Top up as little as you need. Most developers spend under $5 in their first month of testing.
• Every model, no restrictions — Your paid balance gives you immediate access to every frontier model on the platform — no "free tier only" model limitations.

New accounts may receive promotional starter credits from time to time. Check the Dashboard after signing up.

We provide access to 200+ models across all major categories: LLMs (GPT-4o, Claude Opus 4.8, Gemini 2.5 Pro, DeepSeek V3, Llama 4, Mistral Large 3), Vision & Multimodal, Embeddings & Reranking, and Speech & Audio (TTS + STT).

Browse the full live catalog with current per-token pricing at api.onerouter.app/pricing. See Models documentation for category overviews and capability comparisons.

OneRouter charges a small, transparent service fee on top of each provider's base rate. You pay for the tokens you consume plus a margin that covers our infrastructure, routing, global edge network, and support.

Every model's per-token price (service fee included) is visible in real-time on the Model Hub before you make a call. The price you see is the price you pay — no hidden costs, no surprise bills.

There is no monthly subscription and no minimum commitment. Top up any amount and start calling models immediately.

We support multiple payment options for global customers:

• Credit / Debit Cards — Visa, Mastercard, American Express via Stripe. Standard card processing fees apply.
• PayPal — Available in 200+ countries and regions.
• Cryptocurrency — USDT (TRC-20 / ERC-20), USDC, and other major stablecoins. Network gas fees are your responsibility. Crypto payments typically confirm within 10–30 minutes.
• Bank Transfer (Wire) — Available for enterprise accounts (minimum invoice: $500). Processing time: 1–3 business days.

All payments are denominated in USD. Your balance updates immediately for card/PayPal payments; crypto and wire transfers appear once confirmed.

Yes, with the following policy:

• Credit card / PayPal payments — Unused credits are eligible for a refund within 7 days of purchase. The platform service fee (the margin we add on top of provider rates) is non-refundable for tokens already consumed.
• Cryptocurrency payments — Due to the irreversible nature of blockchain transactions, crypto payments are non-refundable. Please test with a small amount first.
• Bank transfers — Refunds are processed within 5–10 business days, less any wire fees.

To request a refund, contact support@onerouter.app with your account email and payment details.

Yes. Unused credits expire 12 months after purchase. This policy allows us to manage provider-side liability while keeping our service fee as low as possible. You'll receive email reminders 30 days and 7 days before any credits expire. Expiration dates are visible in the Dashboard under Billing → Credits.

Auto top-up ensures your balance never drops to zero:

1. Go to Dashboard → Billing → Auto Top-Up
2. Set a threshold (e.g., $5 — when your balance drops below this, we trigger a recharge)
3. Set an amount (e.g., $20 — how much to add each time)
4. Choose your payment method

You'll receive an email receipt for every auto top-up. You can disable or adjust it at any time. We recommend enabling it for production workloads to avoid 402 interruptions.

You have several layers of cost control:

• Per-key monthly budget — Set a hard spending cap per API key. When the key hits its cap, requests are rejected until you raise the limit or the cycle resets.
• Per-model rate limits — Set custom RPM (requests per minute) and TPM (tokens per minute) limits for each API key.
• Model whitelisting — Restrict a key to only specific models (e.g., only allow cheaper models for development keys).
• IP whitelisting — Limit key usage to specific IP addresses or ranges.
• Real-time usage dashboard — Monitor spend by key, model, and time period in the Dashboard.

All limits are configured from Dashboard → API Keys when creating or editing a key. See Key Scoping for details.

Tokens are counted exactly as the upstream provider counts them: prompt tokens + completion tokens = total billable tokens. We pass through each provider's tokenizer so counts match what you'd see calling the provider directly.

For multimodal inputs (images, audio, video): each provider has its own formula for converting media to token equivalents. We pass through the provider's calculation — your dashboard shows the final token count and cost. Generally: images in high resolution are ~85–170 tokens each (GPT-4o), audio is ~50 tokens per second (Whisper).

For models with prompt caching (Claude, GPT-4o), cached prompt tokens are billed at the provider's discounted cache rate. Your usage dashboard breaks down regular vs. cached token spend.

No — we do not store your prompts or completions. Your data passes through our infrastructure in real-time and is not persisted. We log request metadata only (model, token count, timestamp, API key ID) for billing accuracy and abuse prevention. This is necessary to calculate your usage and protect the platform.

We never use your prompts or completions for model training, and we never sell or share your data with third parties.

If you require zero data visibility (i.e., you don't want us to even see metadata), OneRouter is fully self-hostable — deploy behind your firewall with complete data sovereignty. See Can I self-host? below.

This depends on the provider and your settings:

• OpenAI — Does not train on API calls (as of March 2023). Data sent through the API is not used for model training by default.
• Anthropic — Does not train on API data. Claude API data is not used for model improvement unless you explicitly opt in.
• Google (Gemini) — Does not train on paid API usage. Free-tier usage may be subject to different terms.
• Other providers — Policies vary. Check each provider's terms. We recommend reviewing the provider's data usage policy if this is a concern.

For maximum control, self-host OneRouter and configure your upstream API keys with providers that have clear no-training policies. You maintain full control over which providers your data touches.

All API keys are encrypted at rest (AES-256). Keys are shown only once at creation — we cannot recover a lost key (you generate a new one and revoke the old). All API traffic is encrypted with TLS 1.3 in transit. We recommend using API keys with IP whitelisting, model scoping, and monthly spending caps for defense in depth. Rotate keys every 90 days as a security best practice.

Our hosted platform is built to align with the following standards:

• SOC 2 Type II — Annual third-party audit of our security, availability, and confidentiality controls.
• ISO 27001 — Information security management system (ISMS) certified.
• GDPR — Data processing aligned with EU General Data Protection Regulation requirements. EU-based data subjects can request data deletion at any time.
• CCPA — California Consumer Privacy Act compliant. California residents have the right to know, delete, and opt out of data sharing.
• HIPAA — Eligible for Business Associate Agreements (BAA) on enterprise plans for healthcare workloads.

Enterprise customers can request our latest audit reports and certification documents at support@onerouter.app.

Yes. Our hosted service implements GDPR and CCPA requirements: data minimization (we don't store your prompts/completions), purpose limitation (metadata is only used for billing and abuse prevention), user data deletion on request, and transparent data processing disclosures.

For strict data residency and compliance requirements, self-hosting gives you complete control — deploy OneRouter on your own infrastructure in any region, behind your firewall. Contact support@onerouter.app for a DPA (Data Processing Agreement).

You can delete your account and all associated data from Dashboard → Settings → Account → Delete Account. Account deletion is permanent and irreversible.

Regarding your balance:

• Any remaining credits at the time of deletion are forfeited. We recommend using your balance or requesting a refund before initiating deletion.
• Billing records required by law (payment receipts, invoices) are retained for the statutory period — typically 7 years.
• All other account data (API keys, usage logs, email, settings) is permanently purged within 30 days.

Yes. DPAs are available for enterprise and team accounts. We provide a standard DPA that covers GDPR data processor obligations, subprocessor disclosures, cross-border transfer safeguards (SCCs), and breach notification commitments. Contact support@onerouter.app with your legal team's requirements — typical turnaround is 2–3 business days.

Yes, 100%. Change base_url to https://api.onerouter.app/v1 and your existing OpenAI SDK code works instantly — Python, Node.js, Go, curl, or any OpenAI-compatible library.

Supported features:

• Chat Completions — Full support including system/user/assistant messages
• Streaming — SSE (Server-Sent Events) with stream: true
• Function / Tool Calling — Parallel tool calls, strict mode
• JSON Mode — Structured output with response_format
• Vision / Image Input — URL and base64 images
• Embeddings — Full support across multiple providers
• Audio — TTS (text-to-speech) and STT (speech-to-text / Whisper)
• Images — Generation via DALL·E and compatible models
• Rerank — Full support
• Reasoning Effort — Control reasoning depth via model suffixes (see below)

Append a suffix to the model name to control reasoning depth:

If no suffix is provided, the model's default reasoning level is used. This lets you trade off speed and cost against answer quality per request, without changing your integration code. See Models → Reasoning Effort for details.

Beyond reasoning suffixes, OneRouter supports routing-oriented variants that control how your request is dispatched:

Combine suffixes where supported: e.g., gpt-5-high-fast for maximum reasoning with the lowest-latency routing. See Models documentation for per-model suffix compatibility.

Yes. Prompt caching is automatically applied when the upstream provider supports it (Claude, GPT-4o, Gemini). When you send the same prompt prefix across multiple requests, the provider caches the computation and charges you a discounted rate for the cached portion — typically 90% off the full prompt token price.

You don't need to change your code. OneRouter passes through the cache status from the provider, and your dashboard shows cached vs. uncached token usage. To maximize cache hits:

• Keep static content (system prompts, context documents) at the beginning of your prompt
• Put dynamic content (user messages, latest queries) at the end
• Reuse the same system prompt across requests

Read the full optimization guide: Prompt Caching.

Yes. OneRouter supports Bring Your Own Key — you can add your own OpenAI, Anthropic, Google, or other provider API keys in the Dashboard. When you configure BYOK:

• Requests for that provider are routed through your key, not OneRouter's pool
• You pay the provider directly — OneRouter adds no service fee on BYOK requests
• You can still use OneRouter's unified endpoint, failover, and cost tracking
• Mix BYOK keys with OneRouter's pool: use your keys for your primary provider and fall back to our pool for others

BYOK is ideal for teams with existing provider relationships, enterprise discounts, or strict billing separation requirements. Configure it from Dashboard → Settings → Provider Keys.

OneRouter returns standard HTTP status codes:

We recommend implementing exponential backoff with jitter for 429 and 5xx errors. See Error Codes for the complete reference with error response bodies.

We target 99.9% uptime for our hosted API. Our infrastructure is horizontally scaled across multiple availability zones with no single point of failure. For mission-critical workloads, self-hosted deployments give you full control over your availability targets.

Enterprise plans include a formal SLA with uptime commitments, credit penalties, and priority incident response. Contact support@onerouter.app for SLA terms.

OneRouter automatically fails over to your next preferred model. Our system:

1. Detects provider unavailability (5xx errors, timeouts) within seconds
2. Skips providers with recent outages (30-second cooldown window)
3. Routes to your next model in the failover chain (configurable in Dashboard → Channels)

A well-designed chain (e.g., GPT-4o → Claude Opus → Gemini Pro) ensures zero dropped requests. You pay only for the model that ultimately serves the request — failed attempts are not billed. See Auto Failover for setup instructions.

OneRouter adds minimal routing overhead — typically under 50ms for API requests. The dominant latency factor is the upstream model's generation speed (time-to-first-token and tokens-per-second), which is unaffected by routing through OneRouter.

For latency-sensitive applications:

• Enable streaming (stream: true) so users see tokens as they're generated
• Use the -fast model suffix to auto-route to the lowest-latency provider
• Deploy a self-hosted instance in your application's region for zero network overhead

Yes. Check the API Status Page for real-time service health, incident history, and scheduled maintenance windows. Subscribe to incident notifications via email, Slack, or webhook — see Webhooks for setup.

Log in to the Dashboard, go to API Keys, and click + New Key. Give each key a descriptive name (e.g., "production-backend", "mobile-app-dev", "staging-test"). You can create unlimited keys.

We strongly recommend creating separate keys for each environment (development, staging, production). Each key has independent usage tracking, spending limits, and model scoping — making it easy to monitor costs per environment or per client. If a development key is compromised, your production key is unaffected.

Revoke it immediately from the Dashboard — revocation takes effect instantly (under 60 seconds propagation). Generate a new key and update your application. Monitor the usage logs for any suspicious activity on the old key before deleting it.

Prevention best practices:

• Use IP whitelisting to restrict where keys can be used from
• Set monthly spending caps to limit blast radius if a key leaks
• Rotate keys every 90 days
• Never commit keys to version control — use environment variables or a secrets manager

Create a separate API key for each environment from the Dashboard:

• Development — Tight spending cap ($10/month), restrict to cheaper models, no IP restriction (for local dev)
• Staging — Moderate cap ($50/month), same models as production, IP-restricted to your staging servers
• Production — Higher cap as needed, all models, IP-restricted to your production servers

Each key has its own usage dashboard, alerts, and activity log. This setup gives you per-environment cost visibility and prevents a dev-phase bug from burning through your production budget. See Key Scoping for the full configuration reference.

Yes. OneRouter is powered by the open-source New API gateway (AGPL-3.0). Deploy via Docker, Docker Compose, or Kubernetes on your own servers. Self-hosting gives you:

• Complete data sovereignty — no data ever leaves your infrastructure
• Full logging control — you decide what gets logged and where it's stored
• Zero latency overhead — deploy in your application's region
• Unlimited customization — modify the open-source code to fit your needs

See the GitHub repository for deployment guides, Helm charts, and bare-metal installation scripts.

Yes. OneRouter supports white-label deployments — rebrand the platform with your own logo, domain, and pricing, then resell AI API access to your customers. The built-in billing, user management, quota system, and multi-currency support make it ready for reseller operations.

Common white-label use cases: regional AI API providers, vertical-specific AI services (legal, medical, education), and value-added resellers bundling API access with consulting or tools. Contact support@onerouter.app for white-label setup guidance and licensing.

Yes. Enterprise plans include:

• Dedicated account manager — Single point of contact for all questions
• Priority support — Guaranteed response times (typically under 2 hours for critical issues)
• Custom SLA — Uptime commitments with credit penalties tailored to your needs
• Consolidated invoicing — Net-30/60 terms, purchase orders, multi-currency billing
• Custom rate limits — RPM/TPM limits scaled to your workload
• Deployment assistance — Architecture review, Helm chart customization, on-premise setup

Contact support@onerouter.app with your requirements — we'll put together a proposal within 1 business day.

Our hosted infrastructure currently processes data across global edge locations for optimal latency. For strict data residency requirements (e.g., GDPR data must stay in the EU, or specific national regulations), OneRouter is fully self-hostable — deploy on your own servers in any region, behind your firewall, with complete data sovereignty.

Enterprise customers can also discuss dedicated region deployments managed by our team. Contact support@onerouter.app for availability in your target region.

We offer multiple support channels:

• Email — support@onerouter.app for billing, account, and technical questions. We respond within 24 hours; most questions are resolved in a single exchange.
• GitHub — github.com/QuantumNous/new-api for bug reports, feature requests, and self-hosting questions. Check existing issues before opening a new one.
• Discord — Community chat for quick questions, integrations, and best practices. (Invite link in the Dashboard footer.)
• Status Page — API Status for real-time incident updates. Subscribe for notifications during outages.

Enterprise customers receive a shared Slack channel with our engineering team for real-time collaboration.