FlexInference: Drop your AI costs today

A router that drops cost by 45%<br>We find cheaper inference within the SLA you provide.<br>svg]:px-4 rounded-full">Get startedsvg]:px-4 rounded-full">Sign in

−45%costs<br>$11.13

without FlexInference<br>$6.04

with FlexInference

input + output / 1M<br>−47%latency<br>167 ms

without FlexInference<br>88 ms

with FlexInference

time to first token

// median cost and latency across 24,458 requests

Some of the ways you can drop your costs by half<br>Play the Gemini Image Classification demo<br>Gemini Image Classification+20.2% Latency-38.9% Cost

Play the OpenAI Deep Research demo<br>OpenAI Deep Research-30.1% Latency-44.8% Cost

Play the OpenAI Browser Agent demo<br>OpenAI Browser Agent+9.7% Latency-51.5% Cost

Built so you aren't debugging at 2am<br>3 ms routing across 300 cities.<br>When you make a request it is fulfilled using edge compute. We use Cloudflare workers which is deployed in 300+ cities. Our own routing adds 1-5 milliseconds on a cold start.

Your prompts are never stored or read.<br>Your prompt and its reply just pass through. We never store them and we never read them. Your provider key is envelope-encrypted with AES-256-GCM and locked to your exact org and provider slot, so it decrypts nowhere else, and a key that will not decrypt is treated as missing. So your production key is safe to drop in.

Your discounts, credits, and API tiers stay yours.<br>You bring your own key, so the provider bills you directly. We also don't have a fee per request. By bringing your own key you also get the benefits of using your credits, discounts, negotiated rates, and API tiers.

We fail fast and loud.<br>If you send a wrong parameter we don't quietly strip it to force a success. When the provider rejects a request, we send the status code and the error back to you. That way you can debug based on your intentions and not find a bug weeks after launching.

Your existing client works unchanged.<br>Point the base URL at us and pass your key. We work with OpenAI, Anthropic, and Gemini clients. To use FlexInference you just need to add a single new field, start_within. If you decide to use our Python or TypeScript SDKs then you also get the benefits of strict types.

Errors your agent can fix itself.<br>Every error comes back in the shape of the SDK you called, so your client parses it unchanged. It carries a machine-readable code, the exact fix, and a doc_url. Our MCP server goes further. Coding tools like Claude and Cursor can search the docs, look up any error code, and manage your keys over OAuth. So your agents fix their own mistakes, and you are not stuck babysitting them.

Only pay when we save you money.<br>100%off

Base price<br>5.5% per request$0per request<br>No fee per standard request<br>No sales call<br>No seats or tiers<br>No trial<br>Routing is free. When you give us an SLA to find a cheaper way to run your request, we hunt for cheaper inference. If we find you cheaper inference, we keep 20% of what we save you. If we cannot find anything cheaper, we escalate your request to a standard request and it is once again free.<br>If we take a $10 request down to $5, we take a $1 fee and you pay $6. That is 40% savings.

svg]:px-4 rounded-full">CLICK TO ACTION*this takes you to login/signup

No new SDK semantics to learn.<br>Point your base URL at FlexInference, pass your FlexInference key, and add start_within to start saving.<br>OpenAIGeminiAnthropic<br>curl https://api.flexinference.com/v1/responses \<br>-H "Authorization: Bearer flex_live_..." \<br>-H "Content-Type: application/json" \<br>-d '{<br>"model": "gpt-5.2",<br>"input": "Summarize this thread.",<br>"start_within": "00h-00m-30s"<br>}'

svg]:px-4">Python SDKsvg]:px-4">TypeScript SDK

Why I built FlexInference?<br>Hey! My name is Adi.<br>I grew up wanting to help others. Actually, that's not always been true. I went through a tough time in college and it made me want to help people. Help people get educated. Help people get better healthcare. Help people with the basics, you know? At first I tried to do that directly. Made a few free websites/tools/videos. And it definitely helped. But, not the scale I wanted.<br>Then AI hit an inflection point. It started making education better because it could answer a billion questions happily. It made healthcare better by personalizing it to everyone. I realized something then. I hadn't built the models, but I could help make them easier to reach. The labs want the same thing. They're working to make inference cheaper, faster, and open to everyone. The problem is all the layers sitting on top. They slow it down, mark it up, and gate who gets in.<br>So I made FlexInference as a crack at that. It makes getting to these providers cheaper, faster, and more reliable. The first way it does that is by hunting for cheaper inference, and escalating to standard when it can't find any. By making it cheaper to work with these models, ideally we can get more ideas out there. More incredible products. And as such, help more people.<br>That's why I created FlexInference. Hopefully, it helps you...