Stats

QuickSilver Pro by the numbers

Honest stats only. Aggregate counters (tokens served, dollars saved) go live as the user base grows enough for the numbers to be credible — see the "Live counters" note below.

Live service status

Live check against the API, cached for 3 minutes. Per-model probes on the status page.

Open Status

Catalog facts

static · built from model-catalog.json v68 · updated 2026-10-28

Claude Opus 5.5 vs Anthropic list: 75%; Claude Opus 5.5 at $1.00 / $5.00 per 1M tokens — 75% below Anthropic list. New: Kimi K3.1 Pro at OpenRouter list parity, $2.00 / $10.00 per million tokens · Highspeed: $4.00 / $20.00 per million tokens. Claude Haiku 5.5 75% below list · Claude Sonnet 5.5 75% below list. New: Gemini 4 Argon, Google's new flagship reasoning model, at an introductory $2.00 / $10.00 per million tokens. New: Bria FIBO 2.0 image generation at $0.055 per image. New: GPT-6.1 Terra at OpenAI list parity, $1.00 / $5.00 per million tokens.
Models served: 91; GPT-6.1 Sol, Claude Opus 5.5 + Sonnet 5.5 + Haiku 5.5, Gemini 3.8 Flash, Grok 4.7, Qwen3.8 Max, GLM-5.3, DeepSeek V4.1, Mistral Large 4, Kimi K3.1 Pro, MiniMax M3, plus image generation. Full list.
Provider comparisons: View all; OpenRouter, Together AI, Fireworks, DeepInfra, OpenAI. Checked dates shown where available.
Languages: 4; English, 中文, Русский, हिन्दी — localized docs + pricing.
vs. OpenRouter: Varies by model; Claude costs 75% less; Qwen 3.7 Plus and MiniMax M3 cost ~20% less. GLM-5.3, Kimi K2.6 and other models match their selected OpenRouter endpoints. Compare exact input and output rates.
vs OpenAI o3-mini: 6×; DeepSeek V4 Pro vs OpenAI o3-mini output pricing. Breakdown.
Launch bonus: $50; Your first top-up is matched up to $50, credited on your next top-up. Standard pay-as-you-go after. No card needed to sign up.

Live counters

not published yet

Token-throughput and aggregate-savings counters go live once the user base is large enough for the numbers to be credible without caveats. Prefer ambitious-honest over "we served 400 tokens yesterday." Watch this space.

Tokens this month: Not published
Saved vs OpenAI: Not published
Requests / sec (p50): Not published

Try QuickSilver Pro

Built by MachineFi Labs.