Live on Solana + Base

The routing layer for autonomous AI.

One API key. 200+ models. 15+ providers. Intelligent routing with sub-second x402 settlement — built for agents that don't wait.

200+Models
15+Providers
~1.2sAvg latency
99.9%Uptime
35M+ x402
transactions settled
200+ models
available instantly
15+ providers
globally routed
Sub-1s
settlement time
DEEPSEEKQWENGLM-4KIMISOLANABASEX402OPENAIANTHROPIC
DEEPSEEKQWENGLM-4KIMISOLANABASEX402OPENAIANTHROPIC

CORE CAPABILITIES

Everything your agents need.
Nothing they don't.

SMART ROUTING

Intelligent multi-provider routing

Real-time EMA health scoring across every provider. Automatic failover, latency optimization, and provider reputation weighting — all invisible to your agent.

OAI
ANT
DSK
QWN
GLM
KMI
Explore routing

X402 PAYMENTS

Native micropayments

HTTP-native payment protocol. No wallets, no friction. Sub-second settlement on Solana and Base.

sub-1s
Median settlement time

AGENT DISCOVERY

Machine-readable identity

"name": "hober",
"protocol": "x402",
"chains": ["solana", "base"],
"models": 200,
"verified": true
View agent card

COMMERCE

One gateway to every major provider

Route to the best available model for each request. Automatic cost optimization, capability matching, and quality monitoring — across every top-tier provider.

OpenAI
Anthropic
DeepSeek
Qwen
GLM-4
Kimi
Explore commerce
Uptime99.9%
Providers6 live
Avg latency~1.2s
Settlementx402

INTEGRATION

Drop-in OpenAI replacement.

Two lines. That's the entire migration. Your existing code stays exactly the same — just swap the base URL and you're routing through Hober's global network.

OpenAI-compatible API
Streaming supported
Zero lock-in
before.ts
// Before: Direct provider
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.openai.com/v1',
  apiKey: process.env.OPENAI_API_KEY,
});
Switch to Hober
quickstart.ts
// After: Hober gateway
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://hober-gateway.fly.dev',  apiKey: process.env.HOBER_API_KEY,});

THE ROUTING LAYER

How Hober works

From request to settlement in under a second.

1

Request

Your agent or app sends an inference request through Hober's OpenAI-compatible API.

POST /v1/chat/completions
Authorization: Bearer hbr_...
2

Route

Intelligent auto-routing selects the optimal provider based on latency, cost, quality, and health scores.

DeepSeekQwenGLMKimiOAIANT

200+ models, 15+ providers

3

Execute

The selected provider processes inference. Hober monitors in real-time with automatic failover.

Healthy
avg ~1.2s
4

Settle

x402 micropayment settles on Solana in sub-second finality. No invoices, no billing cycles.

SolanaBase

Sub-second settlement

Your agents deserve better infrastructure.

Start routing in minutes. No credit card required.

Get started — it's free