Skip to content
All features
AI runtimepackages/ai/llm-gateway

llm-gateway package

Provider-routing edge for LLM calls — fallback chains, per-tenant quota, response caching, usage metering wired in.

Open docs
Stability
Stable
Scope
Global
Boundary
packages/ai/llm-gateway

llm-gateway

packages/ai/llm-gateway

AI runtime · tool registry · MCP boundary

Ready

Capability graph

ai/llm-gateway
llm-gateway
Tool policy
Stream UI
Output

Run ledger

  1. 1
    Input
    packages/ai/llm-gateway/request
  2. 2
    Plan
    message reducer -> model turn
  3. 3
    Tool policy
    tool schema · auth scope · rate limit
  4. 4
    Stream UI
    events -> UI state machine
  5. 5
    Output
    @nebutra/agents response envelope
p50 latency
76 ms
events/sec
409/s
providers
3
eval score
79
Usagellm-gateway.ts
typescript
llm-gateway.ts
1import { llmGateway } from "@nebutra/llm-gateway";
2
3const result = await llmGateway.run({
4  tenantId: org.id,
5  // llm-gateway is part of the AI runtime — composable with other AI primitives.
6  input: payload,
7});