AI runtimepackages/ai/ai-providers
ai-providers package
Provider metadata — pricing per million tokens, context windows, modalities. Drives model selection and cost estimates.
- Stability
- Stable
- Scope
- Global
- Boundary
- packages/ai/ai-providers
ai-providers
packages/ai/ai-providersAI runtime · tool registry · MCP boundary
Ready
Capability graph
ai/ai-providersai-providers
Tool policy
Stream UI
Output
Run ledger
- 1Inputpackages/ai/ai-providers/request
- 2Planmessage reducer -> model turn
- 3Tool policytool schema · auth scope · rate limit
- 4Stream UIevents -> UI state machine
- 5Output@nebutra/agents response envelope
p50 latency
99 ms
events/sec
608/s
providers
4
eval score
80
Usageproviders.ts
typescriptproviders.ts
1import { resolveProvider } from "@nebutra/ai-providers";
2
3const { provider, model } = resolveProvider("claude-sonnet-4-6");
4// → { provider: "anthropic", model: "claude-sonnet-4-6", contextWindow: 1_000_000 }
5
6const fallback = resolveProvider("openai/gpt-5.5", {
7 fallback: "anthropic/claude-haiku-4-5",
8});