Wisdom Gate
LLM APIs, AI Models, AI Saas
Hey folks,
Until now we’ve been running entirely on the free tier. That means everyone gets 50 DeepSeek calls a day, which worked great until usage exploded. The load got wild, especially on Sora 2 and Claude channels, so we had to bring in some structure.
We just rolled out Starter ($5), Pro ($19.9), and Premium ($49.9) plans. Not subscriptions with fine print, just straightforward upgrades that unlock better throughput, stable routes, and new model access (Claude Sonnet 4.5, GPT-5 Codex, Sora 2, Veo 3.1, etc.).
For most devs, Pro is the sweet spot. It gives $30 monthly credit, a 5% discount on all models, and access to the same fast channels we use internally.
If you’re just tinkering, the free plan still stays as-is — no limits changed there.
We’re still shipping fast. If you’ve got feedback on pricing, stability, or what models you’d like us to add next, I’d love to hear it.
You can try the API or studio here:
Happy to answer any questions, and really appreciate anyone testing or breaking things.
This month, Wisdom Gate expanded its lineup with ten new models across LLM, Video, and Coding categories.
🧠 LLM Models
DeepSeek V3.2 Exp — Enhanced long-context reasoning and performance.
Gemini 2.5 Pro — Advanced multimodal understanding with balanced speed and quality.
Claude Haiku 4.5 (20251001) — Compact, fast, and refined conversational capability.
🎬 Video Models
Veo 3.1 — High-fidelity short video generation.
Veo 3.1 Pro — Extended duration and cinematic quality.
Sora 2 — Realistic motion synthesis for creative projects.
Sora 2 Pro — Supports asynchronous generation and higher resolution output.
💻 Coding Models
GPT-5 Codex — Optimized for end-to-end code workflows.
Qwen 3 Max — Excellent multi-language and logic performance for developers.
Claude Sonnet 4.5 Thinking (20250929) — Advanced reasoning and debugging companion.
All new models are available via the Wisdom Gate API Console and Studio.
Explore them today: https://wisdom-gate.juheapi.com/models
We’re building Wisdom Gate, an API gateway for LLMs so devs can hit multiple models through one clean interface.
What’s new this week
Claude Sonnet 4.5 is live on Wisdom Gate (Text + Image, up to 1M context).
Pricing: 20% off the official list right now — $2/M input and $10/M output.
Why we’re building this
Managing multiple LLM vendors (auth, pricing, regional routing, failovers) is annoying. We want one key, one SDK, sane routing, and clear cost controls.
What’s hard right now (and how we’re fixing it)
Our free DeepSeek endpoints were hammered by automated traffic (hundreds of thousands of calls/hour). Result: 429/400 spikes for normal users.
Mitigations shipping: more DS capacity, per-IP and per-key rate windows, burst queues, anomaly throttles, and better observability.
Support backlog is catching up; we’re improving status updates and automatic incident notices.
Ask for feedback (would love IH input)
What’s your favorite way to separate free vs paid rate-limits without punishing legit power users?
For models with “thinking” modes, would you rather pay a premium per output token, or a small thinking-token surcharge only when used?
Do you prefer a single aggregated key with routing rules, or per-provider keys exposed in the dashboard?
Roadmap (next 2–4 weeks)
Per-model budgets/alerts
Cached completions and idempotency keys
Better logs: latency and cost breakdown
If you’re curious, try Sonnet 4.5 and tell me where it breaks in your workflow. I’m here all day answering questions and would love brutal feedback. If you need stable access while we scale free DS, the paid route is unaffected.
Thanks for reading — happy to swap notes with anyone building infra or devtools.
(P.S. If you want a quick link or code for the top-up bonus, ping me and I’ll DM.)
Comment