One OpenAI-compatible API for every major model. Requests are routed to providers we have verified, billed at or below list price, with volume discounts on request and per-request insight into cost, speed and savings.
Free credit to start · Base URL api.osmexo.com/v1
curl https://api.osmexo.com/v1/chat/completions \
-H "Authorization: Bearer $OSMEXO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'
Three things every team needs from an AI gateway, and the reason each one saves money.
List price or lower on every model, no platform fee, and volume discounts you request per model instead of negotiating with five vendors.
A provider only serves your traffic after automated checks confirm the right model, a correct answer and acceptable latency. Failing sellers never answer you.
Cost, tokens, time to first word and the route taken, per request. Budgets per key, limits per organization, alerts when spend looks wrong.
If your code speaks OpenAI, it already speaks OSMEXO.
Sign up, verify your email and create an API key. New accounts start with free credit, so the first calls cost nothing.
Point your OpenAI SDK at https://api.osmexo.com/v1 and use your OSMEXO key. Same request shapes, same streaming, one bill.
Every response carries its cost. The dashboard shows spend, speed and what the same traffic would have cost direct, per key and per model.
import os
from openai import OpenAI
client = OpenAI(base_url="https://api.osmexo.com/v1", api_key=os.environ["OSMEXO_API_KEY"])
reply = client.chat.completions.create(model="anthropic/claude-sonnet-4", messages=[{"role": "user", "content": "Hello"}])
Live prices from the catalog. What you see is what you are billed, per million tokens, in USD.
| Model | Vendor | Input / 1M | Output / 1M | Routes |
|---|---|---|---|---|
GPT-4o mini openai/gpt-4o-mini · 128k ctx | OpenAI | $0.15 | $0.6 | 1 |
Claude Sonnet 4 anthropic/claude-sonnet-4 · 200k ctx | Anthropic | $3 | $15 | 1 |
DeepSeek V4 Flash deepseek/deepseek-v4-flash · 128k ctx | DeepSeek | $0.14 | $0.28 | 3 |
Same models, same output. The difference is everything around the call.
| Direct with each vendor | With OSMEXO | |
|---|---|---|
| Accounts and keys to manage | One per vendor | One |
| Invoices | One per vendor, in several currencies | One prepaid balance |
| Price per token | List | List or lower |
| Volume discount | Negotiate with each vendor | Request per model in the dashboard |
| When a provider fails | Your users see an error | Automatic fallback to a verified route |
| Provider quality | You find out in production | Verified before it serves you |
| Cost visibility | Monthly, per vendor | On every response, per key |
| Payment | Card per vendor | USDC, PayPal, Venmo, Cash App, Wise; card soon |
Prepaid credits, debited per token. No subscription, no seats, no minimum commitment.
From any wallet, no account needed. Exact amount, credited about 20 seconds after you send. You only pay network gas.
US dollars through Peer Pay. Approved in a few minutes, no fee on your side.
Visa, Mastercard and American Express. Coming soon.
Every model is priced at the vendor’s published list price or below, and there is no platform fee on top. Because we route across several providers for the same model, we can grant volume discounts per model. Each response tells you what the same tokens would have cost direct.
From the dashboard you pick a model you use a lot and ask for a better rate. We review the request, usually within a business day, and the approved discount applies to every call to that model from then on. Nothing to renegotiate with each vendor.
A provider only serves a model after our automated checks confirm it returns the right model, a correct answer and acceptable latency. Providers that fail or drift are removed from rotation automatically. You never call an unverified path.
Only the base URL and the key. The gateway speaks the OpenAI wire format for chat, responses, embeddings, images, speech and transcription, so the official OpenAI SDKs and most frameworks work as they are.
Prepaid credits, from $1. Pay with USDC on Base from any wallet, or in US dollars through PayPal, Venmo, Cash App or Wise. Card payments are coming. There is no subscription and no seat fee.
The gateway retries and falls back to the next verified provider for that model before the first token is sent, so your users see a slower answer instead of an error. You can see which route answered on every request.
Yes. Set a monthly limit for the organization, a daily or monthly budget per API key, and a low-balance alert. Purchases are capped per day and per month and can be raised on request. Unusual spend triggers an alert.
No. Prompts and completions pass through to the provider you are routed to and are stored only as much as you choose for your own request logs. Keys are stored hashed and secrets are never logged.
Create a key, change the base URL, and see on the very first response what you saved.