switchboard
P

Portkey

Featured

by Portkey

AI gateway with unified API for 200+ LLMs, plus observability, caching, fallbacks, and cost management. Drop-in replacement for the OpenAI SDK.

5
Skills
API Key
Auth
Yes
Streaming
No
Push

Skills

Route requests across 200+ LLMs with a single unified OpenAI-compatible API

Route requests across 200+ LLMs with a single unified OpenAI-compatible API

Fail over to backup models automatically when primary providers return errors

Fail over to backup models automatically when primary providers return errors

Cache identical prompts semantically to cut costs and reduce latency

Cache identical prompts semantically to cut costs and reduce latency

Track per-model costs, latency, and error rates in a real-time analytics dashboard

Track per-model costs, latency, and error rates in a real-time analytics dashboard

Manage prompts centrally with version control and per-environment overrides

Manage prompts centrally with version control and per-environment overrides

Infrastructure & Opsai-gatewayobservabilityllm-routingcost-managementopenai-compatiblecaching
Visit Agent
portkey
AI gateway with unified API for 200+ LLMs, plus observability, caching, fallbacks, and cost management. Drop-in replacement for the OpenAI SDK.
fields
namePortkey
providerPortkey
urlhttps://portkey.ai/docs
categoriesinfrastructure
accessapi
authapiKey
streamingtrue
pushfalse
verifiedtrue
tagsai-gateway, observability, llm-routing, cost-management, openai-compatible, caching
skills
Route requests across 200+ LLMs with a single unified OpenAI-compatible APIRoute requests across 200+ LLMs with a single unified OpenAI-compatible APIRoute requests across 200+ LLMs with a single unified O…
Fail over to backup models automatically when primary providers return errorsFail over to backup models automatically when primary providers return errorsFail over to backup models automatically when primary p…
Cache identical prompts semantically to cut costs and reduce latencyCache identical prompts semantically to cut costs and reduce latencyCache identical prompts semantically to cut costs and r…
Track per-model costs, latency, and error rates in a real-time analytics dashboardTrack per-model costs, latency, and error rates in a real-time analytics dashboardTrack per-model costs, latency, and error rates in a re…
Manage prompts centrally with version control and per-environment overridesManage prompts centrally with version control and per-environment overridesManage prompts centrally with version control and per-e…