Shutterai

Overview / Description

Shutterai (branded ShuttleAI) is an AI LLM gateway tool that gives developers a single unified API to call multiple large language models for text generation, image generation, and agent building. Instead of integrating each provider separately, teams route requests through one OpenAI-compatible endpoint that reaches models including GPT-5.2, GPT-5, Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5, and open-source GPT-OSS 20B and 120B. A "ShuttleAI Auto" dynamic router can pick a model per request, and the platform curates a smaller set of reliable models rather than exposing every option. Access is subscription-based rather than pure pay-per-token: plans set both a request-per-minute rate limit and a context-window ceiling, from Free (2 req/min, 8K context, 1,000 requests/month) up to Scale (80 req/min, 128K context). It ships API documentation, examples, and SDKs to shorten setup. Shutterai fits developers and small teams who want multi-provider model access behind one billing relationship and one integration. Note the tool is early and thinly documented publicly, and the api.shutterai.win host was unreachable at review time, so verify current models and limits on the official site before committing.

Used For

Developers and small teams use Shutterai to access multiple LLMs (GPT, Claude, open models) through one unified API with flat subscription pricing.

Pricing

Free

$0/month

$0/mo (1,000 requests/month, 2 req/min, 8K context)

View pricing

Basic

$10/month

$10/mo (10 req/min, 16K context)

View pricing

Premium

$25/month

$25/mo (30 req/min, 36K context)

View pricing

Scale

$75/month

$75/mo (80 req/min, 128K context)

View pricing

Enterprise

Free

Custom pricing

View pricing

Pros & Cons

Pros

  • Single OpenAI-compatible API reaches many models (GPT-5.2, Claude Opus/Sonnet/Haiku 4.x, GPT-OSS 20B/120B)
  • ShuttleAI Auto dynamically routes each request to a suitable model
  • Flat subscription tiers instead of per-token billing, starting with a free plan (1,000 requests/month)
  • Higher tiers raise both rate limit and context window (up to 80 req/min, 128K context on Scale)
  • Curated model list plus SDKs, examples, and docs to speed integration

Cons

  • Early-stage product with thin public documentation
  • The api.shutterai.win host returned an error and was unreachable at review time
  • Free and lower tiers cap requests per minute (2-10 req/min) and context window (8K-16K)
  • Curated catalog means fewer model choices than broad aggregators

Questions & Answers

Alternatives

OpenRouter, LiteLLM, Portkey, Together AI, Eden AI