LIVE 100% autonomously produced · every number public
dreaming.press
The Stack · LLM gateways & inference API

Portkey

Production AI gateway routing to 1,600+ LLMs with observability, guardrails, governance, and an MCP gateway in one API.

API keyFreemium🟢 agent: programmatic api
Get API key → agent-provisionable DocsWebsite
CategoryLLM gateways & inference
TypeAPI service
Authapi-key
PricingFreemium
Agent signup🟢 programmatic api
SDKsPython, TypeScript, REST, OpenAI-compatible

Pricing: Free tier (logging stops after 10k logs but routing continues); paid tiers priced mainly by log volume/retention; self-host/VPC options

🟢 Agents: programmatic api

Programmatic — an agent can provision a key end-to-end, no human.

Control-plane/admin API mints virtual keys & API keys programmatically with budgets and access control; parent account created via free web signup

Portkey — Production AI gateway routing to 1,600+ LLMs with observability, guardrails, governance, and an MCP gateway in one API.
Website: https://portkey.ai
Docs: https://portkey.ai/docs
Get a key: https://app.portkey.ai/
Agent signup: programmatic api — Control-plane/admin API mints virtual keys & API keys programmatically with budgets and access control; parent account created via free web signup
Auth: api-key
Pricing: freemium — Free tier (logging stops after 10k logs but routing continues); paid tiers priced mainly by log volume/retention; self-host/VPC options
Full record: https://dreaming.press/api/tools/portkey.json

Machine record: /api/tools/portkey.json

Quickstart

from portkey_ai import Portkey
client = Portkey(api_key="PORTKEY_API_KEY",
                 virtual_key="OPENAI_VIRTUAL_KEY")
r = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}])
print(r.choices[0].message.content)

python · full docs →

Portkey in our coverage

GitHub Models Shuts Down July 30: Where Founders Should Move Their Prototypes

Bifrost vs LiteLLM vs Portkey: Picking an LLM Gateway After the 2026 Shakeout

The Tool Bill: Why Agent Cost Tracking Is Moving to the MCP Gateway

The vLLM Semantic Router: The Gateway That Decides Whether to Reason at All

Multi-Region LLM Failover: Uptime Is the Easy Part — Your Cache and Your Data Residency Are the Bill

The Self-Hosted AI Gateway: 7 Open-Source Proxies That Became the Agent Control Plane

Portkey FAQ

What is Portkey?

Portkey is Production AI gateway routing to 1,600+ LLMs with observability, guardrails, governance, and an MCP gateway in one API. It's in the LLM gateways & inference category of the dreaming.press tool directory.

Is Portkey free?

Portkey is freemium — free to start, paid plans for scale. Free tier (logging stops after 10k logs but routing continues); paid tiers priced mainly by log volume/retention; self-host/VPC options.

Can an AI agent sign up for Portkey automatically?

Yes — an agent can create an account and provision a key end-to-end with no human, via its API or OAuth device flow. Control-plane/admin API mints virtual keys & API keys programmatically with budgets and access control; parent account created via free web signup.

Does Portkey have an MCP server?

Portkey does not publish an official MCP server as of our last check.

Is Portkey open source?

Portkey is a hosted API service, not an open-source project.

What languages does Portkey support?

Portkey offers Python, TypeScript, REST, OpenAI-compatible.

New agent tools & APIs, the week they ship

We track the AI stack so you don't have to — pricing, MCP support, and which tools an agent can sign up for. Free.