Badges — Powered by QuickSilver Pro

Terms — the short version

Badges

You're on a free trial balance. Every reply shows what it cost — the same price the API charges.

Chats are billed to your account balance at standard API rates. Every reply shows what it cost.

Ask anything.

Top up to keep going. The same balance works across the whole catalogue and from the API, with your own key.

Top up to keep chatting — the same balance powers this chat and your API key.

Your trial balance is used up.

Your balance is used up.

New chat

Drop in to the official OpenAI SDK and start building. New accounts start with bonus credits.

When your workload could use open-source quality, QSP is 6×–30× lower than Azure's closed catalog. No resource provisioning, no AAD setup.

QuickSilver Pro vs Azure OpenAI

Claude Opus 5 runs 20% below Bedrock's own per-token rate, DeepSeek V4 Pro is ~68% lower on output than Bedrock's DeepSeek reasoning, and Kimi K3 / GLM 5.2 / the V4 wave aren't on Bedrock at all. Drop-in OpenAI SDK — no SigV4 or AWS plumbing.

QuickSilver Pro vs AWS Bedrock

DeepSeek V4 Pro is 73% lower on output than DeepInfra's current V4 Pro rate, with per-token cache pricing. DeepInfra's cache discount may change the math for cache-heavy prompts.

QuickSilver Pro vs DeepInfra

DeepSeek V4 wave well below Fireworks' own-GPU rates. OpenAI-compatible surface, same tool-calling semantics.

QuickSilver Pro vs Fireworks AI

Different categories: managed token-priced LLM API vs serverless GPU. QSP for stock open-source chat; Modal for custom models or non-LLM workloads.

QuickSilver Pro vs Modal

Managed inference vs containers you deploy on H100s. QSP is faster to ship when you don't have a GPU fleet to fill or strict data-locality requirements.

QuickSilver Pro vs NVIDIA NIM

20% lower on DeepSeek V4 Flash & Pro, Kimi K3, GLM 5.2, Claude Opus 5, GPT-5.6 and Grok 4.5 at the per-token level. Same OpenAI-compatible API, two-line migration.

QuickSilver Pro vs OpenRouter

DeepSeek V4 wave well below Together's own-GPU rates — the widest gap we hold against any major provider for reasoning-heavy workloads.

QuickSilver Pro vs Together AI

DeepSeek V4 Pro is ~7× lower than Gemini 2.0 Pro on output. Plain OpenAI SDK — no GCP project, service-account JSON, or quota request.

QuickSilver Pro vs Vertex AI

Head-to-head pricing comparisons for QuickSilver Pro vs the competing OpenAI-compatible inference providers, plus per-model use-case guides with quickstart code.

Compare & Use — QuickSilver Pro

Compare & Use

[[qwen3.6-35b.context]] context, 3B active MoE. RAG and long-document summarization at [[qwen3.6-35b.input]] input.

One quick question — it helps us know which channels actually reach developers like you.

How did you find QuickSilver Pro?

Check your inbox

Sign in with your email and password.

Sign in

Set a new password for this account, then we'll sign you in automatically.

Choose a new password

Enter your email and we'll send you a link. This works whether you're resetting a password or setting one for the first time.

Set or reset your password

Beta invite accepted.

This invite has already been claimed.

We'll email you a verification link to finish sign-up. {amount} free credits included.

We'll email you a verification link to finish sign-up. New accounts start with a free trial balance you can spend right away in the browser chat — no card needed.

Create your account

Reset your password below — we'll email you a fresh reset link.

Account already exists.

Links are valid for 30 minutes. Enter your email below to send a fresh one.

Link expired.

We couldn't verify that link. Enter your email below to receive a new one.

Invalid link.

Stripe payment method

Keep your balance above a floor and recharge automatically with a saved card.

Auto Recharge

Save the card you enter and top up {topup} automatically when your balance falls below {threshold} — at most 4 times or $200 per 24 hours. Applies to whichever amount you pick below; fine-tune the rest anytime.

Keep my agent running — auto-reload this card

Credits are added to your key automatically within seconds. No refunds once applied.

Use the same email you registered with.

Friend or partner gave you a code? Apply it here to add {amount} of credits to this account. One per account.

Have a referral code?

Credits never expire. Pay only for what you use.

Buy Credits

Permanently remove your account, all API keys, and any remaining credits. This cannot be undone.

If a key was exposed (leaked to git, shared in a screenshot, posted in logs), use this to immediately revoke all keys. A fresh replacement key will be generated automatically.

Danger zone

Name

Create API key

will immediately start getting 401 errors. This can't be undone.

Delete this key?

Delete your account?

Editing {alias}. This caps the spend that can be charged to this specific key within a 30-day window; other keys are unaffected.

Monthly spend limit

All existing keys will be permanently revoked and stop working immediately. Any app using them will get 401 errors. A fresh replacement key will be generated so you're not locked out.

Your old keys have been revoked. Copy this new replacement key now — you won't see it again after closing this dialog.

All keys revoked

Revoke all API keys?

Create named keys for each app or environment. All keys share your account balance.

API Keys

Full keys are shown only once at creation time. If a key leaks, delete it and create a new one - other keys keep working.

Keep your keys secret.

Top open-source and frontier models at 20% below standard rates.

Models

Paste these three values wherever your agent / CLI / IDE asks for an "OpenAI-compatible endpoint". Keep your key secret.

Connect your agent

Chat with the models right here. Your first messages are on us.

Try it in your browser — no key needed

Your key is provisioned but balance is zero, so the demo call below will 402 until you load credits. Launch bonus: we match your first deposit 100%, up to $50 in bonus credits. Pay $5, get $10.

Top up to enable your key.

Copy this command, paste into your terminal. Costs about

Make your first call

Friends signing up with your link get {amount} in credits on their first top-up. We add the same {amount} to your balance at the same time.

Invite friends — get {amount} each

About {balance} left. Top up now so your API calls don't stop mid-task.

Your balance is running low

Your balance is depleted ({spent} spent so far). Add credits to keep making API calls — same pricing, same models, pay as you go.

You're out of credits

Your account activity and usage at a glance.

Overview

Agent-friendly:

V4 Flash, V4 Pro, and Kimi K2.6 think by default - pass

in the request body for non-thinking low-cost chat. (The Qwen 3.6/3.7 models think by default but the gateway suppresses it for you - pass reasoning.enabled=true to opt in. Some always-reasoning models like Grok 4.5 don't accept this flag - don't send it to them.)

Available models:

Vercel AI SDK users:

Drop-in replacement for OpenAI. Change two lines.

Quick Start

Spend, throughput and latency across your models. Days are UTC.

Usage

Set daily, weekly and monthly spend caps per team, per person and per project. Overspend is blocked automatically — no surprise invoices.

Central budget control

Run self-hosted open-source models for everyday work and call frontier models only when they earn it — you control the ratio.

Low-cost local, capped frontier

Real-time cost dashboards broken down by user, team and model. The AI bill is no longer a black box.

Know exactly where it goes

Stop guessing where your AI budget goes. Set hard limits, see every dollar, and run low-cost local models for daily work while reserving frontier models for what truly matters.

Turn AI spend into a controlled, visible line item

Something went wrong sending your request. Please try again in a moment.

Tell us about your environment and we'll scope a private deployment for your team.

Your request is on its way to our team. We'll reach out at the email you provided.

Thanks — we'll be in touch

Book a demo

Runs in your own network or private cloud, even fully air-gapped. Code and conversations never leave your perimeter.

Private deployment

Freely mix and switch local open-source and paid frontier models. The leverage stays with you.

No vendor lock-in

Upstream credentials and every usage log live on your infrastructure — encrypted and auditable.

Your keys, your logs

Private by default — built for compliance and data residency.

Your AI stays inside your boundary

Claude Code, Codex, Cursor and more work out of the box. Developers copy one line of config and go.

Works with the tools devs already use

Server-side translation lets even a self-hosted open-source model power Claude Code — no local proxy, no per-machine setup.

Any model drives any tool

An admin adds an account, the employee signs in and copies their endpoint. Done.

Zero-friction onboarding

Get your whole team productive on day one.

One endpoint, every tool, any model

Multiple admins, team-scoped permissions, and per-team control over which models and providers are allowed.

Roles, teams and access control

Connect your enterprise SSO (OIDC) and enforce TOTP two-factor for secure, compliant access.

SSO and 2-factor

Every call is traceable for internal review and security requirements.

Full audit trail

You decide who can use what.

Enterprise-grade governance

Load balancing and automatic failover across multiple upstreams — a single provider outage won't stop your team.

High availability

We handle deployment, model integration and training. Optional ongoing operations and support.

Turnkey delivery

Make it yours — your company name, logo and interface.

White-label

Production-ready, with people behind it.

Reliable, and we deliver it

Self-hosted AI gateway for enterprises. One private endpoint for Claude Code, Codex and every agent tool. Mix local open-source and frontier models with central budgets, governance and full cost visibility.

QuickSilver Pro Enterprise — Your company's private AI gateway

One private endpoint for every AI coding and agent tool. Run local open-source models alongside paid frontier models — with central budgets, governance, and full cost visibility, all inside your own network.

Your company's own AI gateway

The page you're looking for doesn't exist or has been moved.

Everything you might want to know about QuickSilver Pro — the OpenAI-compatible inference API for Kimi K3, DeepSeek V4 Flash & Pro, GLM 5.2, Claude Opus 5, GPT-5.6, Grok 4.5 and Gemini 3.5.

FAQ — QuickSilver Pro

Frequently asked questions

Plug in your monthly usage to see what it costs here, next to published list rates.

Estimate your monthly cost

output with stable exit codes — Claude Code, Cursor, Aider can call it without parsing HTML.

Create an account, get your API key in 30 seconds.

Get your API key

Common questions

Open weights and closed frontier in one OpenAI-compatible API — Kimi K3, DeepSeek V4 Pro, Claude Opus 5, GPT-5.6, Grok 4.5, Gemini 3.5. One key, one bill, no subscription, and up to 20% below the standard per-token rate. Change two lines of code.

up to 20% below list.

Kimi K3 to Claude Opus 5,

Customers save 20% today on a curated catalog. The gap comes from a narrow operational surface and tight engineering, not margin shaving. Phase 2 widens the gap as more of the stack moves in-house.

Today: launched on a curated catalog

We're building a self-hosted serving layer on H100/H200 using SGLang + continuous batching, EAGLE-3 speculative decoding, FP8 quantization via DeepGEMM, and SageAttention / ThunderMLA custom kernels. Target: another 30-50% below current prices on the DeepSeek V4 wave.

Next: our own inference stack on dedicated GPUs

Open weights are public, so we can run and optimize them ourselves — that's where the next price cut comes from. Closed frontier models can't be tuned that way, so we hold them below standard list price instead. Both live behind one key: reach for the frontier when a task needs it, open weights when they're enough.

Why the open-weight catalog is the long game

Per 1M tokens for text models · per image where noted.

Frontier and open models. One API. Priced below list.

[[qwen3.6-35b.name]] for [[qwen3.6-35b.context]] RAG →

vs DeepInfra

vs Fireworks

vs OpenAI

vs OpenRouter

vs Together AI

OpenAI-compatible API for frontier and open-weight LLMs — Kimi K3, DeepSeek V4 Pro, GLM 5.2, Claude Opus 5, GPT-5.6, Grok 4.5, Gemini 3.5 — priced up to 20% below standard per-token rates, with every row's reference price linked. Two-line drop-in replacement.

Kimi K3, Claude Opus 5, GPT-5.6, DeepSeek V4 API · up to 20% below list · QSP

The Controller determines the purposes and means of processing Personal Data submitted to the service. The Processor processes that Personal Data solely on documented instructions from the Controller (via API request parameters) and only to provide the service.

Data subjects: end-users of the Controller's application whose inputs are submitted to the API. Categories: content of prompts and completions (which may contain any Personal Data the Controller chooses to send), account metadata, and usage metadata. Duration: for the term of the service agreement.

Process Personal Data only on Controller's instructions, unless required by law (in which case the Processor will notify the Controller first where legally permitted).

Impose confidentiality obligations on personnel authorized to process Personal Data.

Implement the technical and organizational measures described in Section 6.

Not train machine-learning models on Controller Personal Data.

Assist the Controller with data subject requests and regulatory investigations, at the Controller's reasonable cost for non-routine requests.

The Controller authorizes the Processor to engage the sub-processors listed on our Privacy Policy. We will give at least 30 days' notice (by email or dashboard) before adding or replacing a sub-processor. If the Controller reasonably objects, the Controller may terminate and receive a pro-rata refund of prepaid unused fees.

Personal Data may be processed in the United States. For transfers originating in the EEA, UK, or Switzerland, the parties rely on the EU Standard Contractual Clauses (Module Two, Controller-to-Processor) and the UK International Data Transfer Addendum, which are incorporated by reference upon execution of the enterprise DPA.

TLS 1.2+ for data in transit; HSTS enforced.

API keys stored as SHA-256 hashes; shown in cleartext only once at creation.

Webhook signatures verified with HMAC-SHA256 and timestamp freshness window.

Prompt and completion content not persisted to our storage (held in memory only during request processing).

Access to production systems restricted to authorized personnel, with logs retained for investigation.

Hosted on Railway (SOC 2 Type II baseline) and Cloudflare edge.

We will notify the Controller without undue delay, and in any event within 72 hours of becoming aware, of any confirmed Personal Data breach affecting Controller Personal Data. Notifications will include the nature of the breach, categories and approximate number of data subjects, likely consequences, and measures taken.

On termination, we will delete all Personal Data within 30 days, subject to any retention required by law (for tax/accounting, up to 7 years in aggregated, non-personal form). The Controller may export account and usage metadata via the dashboard or by API at any time during the service term.

The Processor will make available to the Controller, upon request, its most recent third-party audit reports (once completed, SOC 2 Type II) or equivalent summaries. Where additional audit rights are required by applicable law, the Processor will reasonably cooperate at the Controller's expense.

In case of conflict between this DPA and the Terms of Service, this DPA controls as to processing of Personal Data.

Data Protection contact: hello@quicksilverpro.io — MachineFi Inc., 68 Willow Road, Menlo Park, CA 94205, USA.

What shipped, and when

Nemotron 3.5 Lightning

Browser chat, no API key required

Qwen3.8 Max

Qwen3.7 Max repriced to Alibaba's own list

DeepSeek V4 Flash 0731, refreshed Gemini, audited open catalog

Claude Opus 5, and Google sign-in

Kimi K3

MiniMax M3, MiMo-V2.5 and Hy3