Frequently asked questions

Seven models: DeepSeek V4 Flash & Pro (1M context, thinking by default), DeepSeek V3 (general chat, coding, tool calling), DeepSeek R1 (reasoning, math), Qwen 3.6 & 3.5-35B-A3B (262K long-context RAG, MoE), and Kimi K2.6 (Opus-class reasoning, 256K context). All served through a single OpenAI-compatible endpoint.

V4 Flash is DeepSeek's newest model (released April 2026): ~74% cheaper output than V3, 1M context vs 128K, and thinks by default (chain-of-thought reasoning) — so a one-token "Hi" can return ~175 reasoning tokens. For V3-style cheap chat without the thinking overhead, pass `reasoning: { enabled: false }` in the request body. Existing V3 keeps working unchanged.

20% below the public per-token rates at OpenRouter, Together AI, Fireworks AI, and DeepInfra on the same open-source models. V4 Flash: $0.08 / $0.16. V4 Pro: $0.348 / $0.696. V3: $0.16 / $0.616. R1: $0.56 / $2.00. Qwen 3.7 Max: $2.00 / $6.00. Qwen 3.6 Plus: $0.26 / $1.56. Qwen 3.6: $0.12 / $0.80. Qwen 3.5: $0.111 / $0.80. Kimi K2.6: $0.584 / $2.79. We don't serve closed models (GPT-4, Claude).

Yes. Change base_url to https://api.quicksilverpro.io/v1 in the official openai Python / Node / Swift SDKs. Streaming, tool calling, json_schema strict mode, and usage.cost accounting all work out of the box.

Yes — any tool that accepts an OpenAI base_url and API key. Set base_url to https://api.quicksilverpro.io/v1, paste your QSP key, and choose any of deepseek-v4-flash, deepseek-v4-pro, deepseek-v3, deepseek-r1, qwen3.6-35b, qwen3.5-35b, or kimi-k2.6 as the model.

Change base_url from api.openrouter.ai/api/v1 to api.quicksilverpro.io/v1. Swap API key. Model IDs: deepseek/deepseek-v4-flash → deepseek-v4-flash, deepseek/deepseek-v4-pro → deepseek-v4-pro, deepseek/deepseek-chat → deepseek-v3, deepseek/deepseek-r1 → deepseek-r1, qwen/qwen3.6-35b-a3b → qwen3.6-35b, qwen/qwen3.5-35b-a3b → qwen3.5-35b, moonshotai/kimi-k2.6 → kimi-k2.6.

Launch bonus: any first purchase between $5 and $50 doubles. Pay $5 and get $10. Pay $50 and get $100. One-time bonus on your first credit purchase. After that it's standard pay-as-you-go.

Yes — we host a free HuggingFace Space at huggingface.co/spaces/MachineFi/QuickSilverPro-Chat where you can chat with the models in a browser. No signup or API key needed.

MachineFi Inc., a Delaware corporation based in Menlo Park, CA. Payments are processed by Stripe and appear on your statement as MACHINEFI INC.