Current
The cheapest AI inference — routed to the path of least resistance, live.
The problem
One channel is
expensive and exposed.
Betting everything on a single inference provider means you overpay, you can't move, and one outage takes your product down with no way to reroute.
Inference you overpay for
List prices swing week to week and you have no leverage. Bound to one channel, you quietly overpay on every single token.
Vendor lock-in
One SDK, one bill, one rate limit. Switching channels means a rewrite, so you stay put even when a cheaper, faster route opens up.
Downtime with no second route
When your one channel degrades or rate-limits you, your product degrades with it. There is no other route to reroute to.
A fragmented ecosystem
Every provider ships a different API, pricing model, and latency profile. Comparing them is a spreadsheet, not a decision.
The solution
One current across every provider
Current sits between your code and the channels — a single endpoint that scores, routes, and reroutes on every request, so inference always takes the path of least resistance without touching your stack.
Integrate once. Reach the whole market.
Point your existing OpenAI SDK at Current and every provider flows behind a single key and a single bill — no new client, no per-provider plumbing.
scored every request · routed to the winner
Smart routing
Every request is scored across channels on price, latency, and reliability in real time — then carried to the winner, with the path it took handed back to you.
Automatic failover
If a channel errors or rate-limits, Current reroutes to the next-best one before a single byte streams. The current always finds a way through.
Cost optimization
Prices drift constantly across the open-model market. Current keeps finding the cheapest channel serving each model so your bill follows the path of least resistance.
The routing engine
Every request is scored,
then carried.
No black box. Each channel earns a single weighted score across cost, latency, and reliability — and the current shows you exactly why it chose the one it did.
Scored against the network right now
The channels
Every channel the current can take
Each provider is a channel. We score every channel that can serve the model on cost, latency, and reliability, send the request down the winner, and keep the rest queued so the current can reroute the moment one fails.
OpenAI-compatible API
Change one line. Keep your code.
Point your existing OpenAI SDK at the Current. One base URL, one key — and every model becomes a channel the routing engine can reach.
from openai import OpenAI
client = OpenAI(
base_url="https://api.thecurrentprotocol.com/v1",
api_key="cur_live_••••",
)
# Same SDK. The Current finds the best channel.
resp = client.chat.completions.create(
model="llama-3.3-70b",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)- /v1/chat/completions
- /v1/completions
- /v1/embeddings
- /v1/models
Pricing
You pay the channel price, plus a flat fee. That's it.
No subscriptions. No per-token markup. We find the lowest-resistance price across every provider and add one transparent, flat routing fee — nothing else.
all-in, per 1M tokens
Pay with Stripe or USDC·Enterprise plans & SLAs·Dedicated channels
Roadmap
From one channel to the default routing layer
One current, flowing downstream — each phase carries the network further toward the default routing layer for open-model inference.
- phase_01shipping
One channel
A single OpenAI-compatible endpoint over every channel, with a live capability registry and routing you can see through.
- OpenAI-compatible API
- Provider registry
- Cost/latency routing
- Console dashboard
- phase_02
Routing that learns
The current adapts. Continuous cost optimization, failover that reroutes around real provider health, and per-request analytics.
- Cost optimization
- Dynamic failover
- Routing analytics
- phase_03
Open the network
Add channels of your own. Bring your own provider, list community providers, and earn a share of the traffic you carry.
- Bring-your-own-provider
- Community providers
- Revenue share
- phase_04
The network layer
The default routing layer for open-model inference — decentralized onboarding and on-chain reputation for every channel.
- Decentralized onboarding
- Provider reputation
Inference takes the path
of least resistance.
One channel. Lowest cost. A current that always finds its way through — across every provider, on every request.