Models
60
Models you can call right now. Input and output prices are listed on this page.
https://api.flyrouter.ai/v1
Smart routing
Charged per request from your USD balance, based on actual usage. Text models are priced per 1M tokens; the grey crossed-out price is the official rate.
Updated 2026-11-18 10:56 UTCBilling rules
| ModelUSD / 1M tokens | Cache read | Cache write | vs official | 24h availability | ||
|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 75% off | |||||
| Claude Opus 5.5 | 75% off | |||||
| Claude Sonnet 5.5 | 75% off | |||||
| Claude Fable 5.2 | 75% off | |||||
| Claude Fable 5.1 | 75% off | |||||
| Claude Fable 5 | 75% off | |||||
| GPT Image 2.6 Flare | from | 78% off | Not monitored | |||
| GPT Image 2.6 Sunburst | from | 78% off | Not monitored | |||
Compatible with major API protocols. Change one line, the Base URL, and you are ready for production;
clients like Codex and Claude Desktop set up in minutes.
Also works with Codex, Claude Desktop, OpenClaw, CC Switch, and any OpenAI-compatible client.
Point your Base URL at FlyRouter, add your API key, and leave the rest of your code as is.
Frontier models, one API. Look up any model’s price on this page.
How we measure thisModels
60
Models you can call right now. Input and output prices are listed on this page.
Time to first token
6.3s
Average time from request to the first token, over the last 24 hours.
Success rate
98.6%
Share of requests that completed successfully over the last 24 hours, across every model.
Run agent workloads reliably at low cost, with model behavior and spend that stay stable and auditable.
Requests go straight to verified upstreams, never silently swapped or downgraded.
Prompts and outputs are used only for routing, metering, and billing. Never trained on, never sold.
Every request's model, token usage, and charge is listed line by line.
One account, one bill. Every upstream provider is vetted by us.
We work with multiple upstream providers, vet each one for quality, and buy from the best, so you don't have to shop around.
We buy credits in bulk from vetted providers and pass the discount straight to you.
Pay as you go. Your balance never expires, with no monthly fee and no minimum spend.
The gateway never rewrites requests: whatever model and protocol you call is forwarded as-is to that model's configured channel. Authentication, groups, quota, and metering all happen before forwarding, and if your balance runs out you get an error, not a cheaper model in disguise.
Swap the Base URL, add your key, and you're live. No new SDK to learn.
Use Claude Code, Codex, or any OpenAI-compatible SDK. Swap the Base URL and keep the rest of your code.
https://api.flyrouter.ai/v1One key for every model. Each request is checked against your balance before it's sent.
Authorization: Bearer sk-…Name the model in your request. We pass it through unchanged, on the provider's native protocol.
POST /v1/chat/completionsResponses stream back as they arrive. Usage is metered per request, and every charge shows up in your logs.
usage.total_tokens: 128406 · Enterprise
Start on a standard enterprise plan, or ask us for a quote based on your volume and use case. We sign a formal contract and issue a VAT invoice.
99.99%
Availability commitment
Up to 90% off
Volume pricing
1 hour
Ticket response
Contract invoice
Contract and bank transfer
Answers to common questions
Sign up, top up in the console, and create an API key. Then point the Base URL in your code or client to https://api.flyrouter.ai/v1 and add your key. Nothing else in your code needs to change.
A unified API that sits between your tools and model providers. You call one endpoint with one key; the gateway forwards each request to the channel for the model you choose, meters usage, and gives you a single consolidated bill.
Yes, and it supports both formats. The OpenAI-compatible endpoint works with the official OpenAI SDK and Codex by changing only the base URL. Claude Code connects through the Anthropic-compatible endpoint with two environment variables.
Yes. Claude Code connects through the Anthropic-compatible endpoint and Codex through the OpenAI-compatible endpoint. Clients like CC Switch and OpenClaw only need the Base URL and your key. See the API docs for step-by-step setup.
Leading frontier models including Claude, GPT, Grok and DeepSeek, with more added over time. The full list, live prices, and official prices are all on the pricing page.
The discount comes from wholesale pricing: we buy upstream capacity in bulk and resell it below official rates, passing the difference on to you. Discounts vary by model, and the pricing page shows current and official prices side by side so you can check.
They are the same kind of product: one key and one bill for models from many vendors. OpenRouter has a far larger catalog, passes through provider list prices and charges a fee when you buy credits. FlyRouter lists mainstream models only, shows each price next to the official one, and accepts Alipay, WeChat Pay and credit or debit cards. See the full comparison
You pay for actual usage, priced in USD. Input, output, and cache prices for each model are listed on the pricing page. You can top up in the console with Alipay, WeChat Pay or a credit or debit card, and your balance is credited instantly.
No. Top up anytime and use credits whenever you like. No subscription required.
Requests that fail because of an upstream outage are not charged. Every call's model, token usage, and charge is logged in the console so you can check them line by line.
Unused balance can be refunded to the original payment method within 7 days of top-up; contact us to request it. Payment processing fees are deducted, and used credit is non-refundable.
No. Prompts and completions are used only for routing, metering, billing, risk control, and support. They are never used for training or sold as usage data.
The status page shows each model's success rate and latency over the last 24 hours. If something looks off, check there first to see whether it's a wider outage.
Email support@flyrouter.ai or use the contact channels in the footer. We'll get back to you as soon as we can.
Pay only for what you use. Credits never expire and are deducted per request in real time,
so your budget lasts longer.
Credits never expire·Top up anytime
One key to a faster, more reliable enterprise AI gateway
| ModelUSD / 1M tokens | Cache read | Cache write | vs official | 24h availability | ||
|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 75% off | |||||
| Claude Opus 5.5 | 75% off | |||||
| Claude Sonnet 5.5 | 75% off | |||||
| Claude Fable 5.2 | 75% off | |||||
| Claude Fable 5.1 | 75% off | |||||
| Claude Fable 5 | 75% off | |||||
| GPT Image 2.6 Flare | from | 78% off | Not monitored | |||
| GPT Image 2.6 Sunburst | from | 78% off | Not monitored | |||