yangmao.ai · Python setup money page

Portkey AI Python API Setup

Use this page when you need a working Python starting point for Portkey AI, then validate quota and model names in the official console before production.

Open official provider → Get one OpenAI-compatible key → Compare API gateway options →

Quick verdict

Free API: Free gateway/developer tier recorded; model tokens still depend on your upstream provider keys or Portkey plan
Rate limits: Portkey plan plus upstream provider quota; verify logs, cache, retries, and spend controls before automation
Best model starting point: openai/gpt-4o-mini
Mainland China access: proxy/relay likely needed

Provider fit matrix

Best fit Fast provider evaluation, prototypes, and fallback routing

Watch out Free credits and rate limits can change without warning

Production fallback Keep at least one compatible backup provider before shipping

Production readiness checklist

Quota gate Start inside Free gateway/developer tier recorded; model tokens still depend on your upstream provider keys or Portkey plan; log usage before adding retries or batch jobs.

No-card check Try the free path first, then confirm whether billing is required for API keys, higher RPM, or production endpoints.

Regional smoke test Run signup, dashboard, DNS, TLS, and first API call checks from mainland China before launch.

Source freshness Snapshot date: 2026-06-18; official quota and pricing can change without notice.

Python setup snapshot

Start with the smallest possible chat completion, then move the key to your server-side secret manager before production.

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["PORTKEY_API_KEY"],
    base_url="https://api.portkey.ai/v1",
    default_headers={"x-portkey-provider": "openai"},
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello from Portkey AI."}],
)
print(response.choices[0].message.content)

Free API and pricing notes

Free gateway/developer tier recorded; model tokens still depend on your upstream provider keys or Portkey plan

Portkey AI is an LLM gateway and observability platform focused on unified keys, routing, caching, logs, retries, and cost controls; its free tier helps build provider fallback but does not automatically mean free model tokens.

Access and production risk

Relay or proxy may be needed

Mainland China reachability must be tested for both Portkey gateway and upstream providers; for China-based users, keep OpenLLMAPI, SiliconFlow, or direct domestic-provider fallbacks.

How to set it up

Create or locate your provider API key in the official dashboard.

Install the OpenAI-compatible Python SDK or the provider-supported SDK.

Set the API key in an environment variable instead of hard-coding secrets.

Run a small Portkey AI chat completion with openai/gpt-4o-mini.

Watch free credits, RPM/TPM limits, response shape, and error messages before scaling.

Portkey AI production validation table

Use this table before sending real users, scheduled agents, or paid traffic to Portkey AI. The goal is to validate source freshness, quota behavior, regional access, and fallback needs instead of trusting a stale free-credit claim.

Check Pass condition If it fails

Signup and billing state Key creation works and the account can spend the recorded Free gateway/developer tier recorded; model tokens still depend on your upstream provider keys or Portkey plan. Compare Portkey AI alternatives or route through a gateway before inviting users.

First request from target region Proxy, relay, or non-mainland deployment path is documented before launch. Do not ship cron jobs or public demos until latency, DNS, TLS, and auth are repeatable.

Quota, retry, and error shape Rate-limit behavior matches the current Portkey plan plus upstream provider quota; verify logs, cache, retries, and spend controls before automation note or official dashboard values. Cap retries, add request logging, and keep a second route for 429/5xx bursts.

Cost per accepted task Real prompts stay within your target token, query, image-credit, or compute budget. Use cheaper primary routes, caching, shorter prompts, or fallback only after validation failure.

Credit-change alerts

Want to know when free credits, pricing, or availability changes? Subscribe first, then compare official providers, API gateways, and alternatives.

Subscribe → Get an OpenLLMAPI key → Compare API gateways →

Source snapshot

Data source: yangmao.ai provider YAML tracker plus provider docs reviewed by the daily crawler. Official dashboards can change quota and pricing without notice; verify before production.

yangmao.ai provider id: portkey-ai
Official source: https://portkey.ai
Last updated: 2026-06-18
Free tier: Free developer plan / trial gateway usage is available; request volume, logs, and team features depend on current plan
API credits: Free gateway/developer tier recorded; model tokens still depend on your upstream provider keys or Portkey plan
Rate limit: Portkey plan plus upstream provider quota; verify logs, cache, retries, and spend controls before automation
Access note: Mainland China reachability must be tested for both Portkey gateway and upstream providers; for China-based users, keep OpenLLMAPI, SiliconFlow, or direct domestic-provider fallbacks.

FAQ

Does Portkey AI have a free API?

Yes. Current yangmao.ai record: Free gateway/developer tier recorded; model tokens still depend on your upstream provider keys or Portkey plan. Rate limit note: Portkey plan plus upstream provider quota; verify logs, cache, retries, and spend controls before automation.

Is Portkey AI OpenAI-compatible?

The recorded setup uses an OpenAI-compatible pattern or SDK-style call. Validate the latest base URL and model names in Portkey AI docs.

Can I use Portkey AI from mainland China?

Portkey AI may need a proxy or relay from mainland China. Test latency and signup before production.

What should I do when Portkey AI credits run out?

Compare the alternatives below, check /en/free-ai-api/, and shortlist official providers or API gateway options before production.