gemini-switch
Multi-provider is the new default — route it, don't overpay

One endpoint. The cheapest modelthat's good enough.

gemini-switch is a drop-in, OpenAI-compatible proxy. Change one base URL and every request auto-routes to the lowest-cost model across Gemini, Claude, and GPT that still clears your quality bar — with real ₹/$ savings shown per route.

No SDK rewrite. No card for the free tier. Cancel anytime.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://switch.aiskillhub.info/v1",  # the only change
    api_key="gsw_live_..."                          # your gemini-switch key
)

resp = client.chat.completions.create(
    model="auto",                                   # we pick the cheapest model
    messages=[{"role": "user", "content": "Summarize this PR"}],
)
Works with the OpenAI SDKLangChain & LlamaIndexVercel AI SDKcURL & anything HTTP

Why teams switch

Cost routing that's honest about quality, with the receipts to prove the savings.

Cheapest-that-fits routing

Each request is scored for difficulty, then routed to the lowest-cost model that clears the quality bar. Easy prompts go to Flash-Lite; hard ones get a frontier model.

Savings shown per route

Every response carries x-gsw-saved headers and your dashboard tallies exactly how many rupees and dollars you kept vs calling a premium model directly.

One-line integration + failover

Change the base URL — that's it. If a provider errors, we fail over automatically so a single outage doesn't take you down.

One bill, every major model

ModelProviderQuality$ / 1M in$ / 1M out
Gemini 2.5 Flash-Litegoogle62/100$0.10$0.40
GPT-5 miniopenai76/100$0.25$2.00
DeepSeek V3deepseek72/100$0.27$1.10
Gemini 2.5 Flashgoogle74/100$0.30$2.50
Claude Haiku 4.5anthropic79/100$1.00$5.00
GPT-5openai91/100$1.25$10.00
Gemini 2.5 Progoogle88/100$1.25$10.00
Claude Sonnet 4.6anthropic93/100$3.00$15.00
Claude Opus 4.8anthropic97/100$5.00$25.00

List prices are approximate and used for routing math; live billing reflects your provider's actual rates.

Simple, usage-based pricing

Free

0/mo
≈ $0/mo
  • Up to 50k requests/mo
  • Auto cost routing
  • Savings dashboard
  • Community support
Start free
Most popular

Pro

1,599/mo
≈ $19/mo
  • 1M requests/mo
  • Cost analytics + export
  • Automatic failover
  • Email support
Choose Pro

Team

3,999/mo
≈ $49/mo
  • 5M requests/mo
  • Custom routing rules
  • Team API keys + roles
  • Priority support
Choose Team

Stop paying frontier prices for easy prompts.

Wire it up in under a minute. See your savings on the first request.

Get your free API key