Kimi K3 to Claude Opus 5,up to 20% below list.
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.
Try it in your browserfree trial balance, no card
- No subscription
- OpenAI compatible
- Pay as you go
- Text + images
- OpenAI SDK
- Aider
- Cursor
- Cline
- Continue.dev
- LangChain
- Vercel AI SDK
1# Two lines. That is the whole migration.2from openai import OpenAI34client = OpenAI(5 base_url="https://api.quicksilverpro.io/v1",6 api_key="your-api-key",7)
Frontier and open models. One API. Priced below list.
Everything about price, in one place — no scrolling required.
claude-opus-5gpt-5.6-solgpt-5.6-lunaclaude-fable-5claude-sonnet-5gemini-3-pro-imagePrices are exact per-token rates, not rounded — some carry more decimals than others. Each struck-through figure is that row's reference list price and links to the page that publishes it, so every line can be checked. "At list" means we sell at the reference price; "mixed" means we are below it on one side and above on the other. Every row checkable, every model verifiable →
Building an agent? Fund a key programmatically with USDC — no account, no card. x402 docs →
Plug in your monthly usage to see what it costs here, next to published list rates.
At 1M input / 300K output the difference is about 4¢. We show real numbers, not big ones — move the sliders to your own volume.
Side-by-side pricing vs every competitor
qspBuilt for terminals and AI agents. --json output with stable exit codes — Claude Code, Cursor, Aider can call it without parsing HTML.
Common questions
QuickSilver Pro is an OpenAI-compatible inference API. The current catalog is DeepSeek V4 Flash, DeepSeek V4 Pro, Qwen3.8 Max, Qwen3.7 Max, Qwen3.7 Plus, Qwen3.7 Flash, Qwen3.6 Plus, Qwen3.6-35B-A3B, Kimi K2.6, Kimi K2.7 Code, Kimi K3, Muse Spark 1.2, Muse Glimmer 30B, GLM 5.3, GLM 5.2, Nemotron 3.5 Lightning, GPT-5.6 Luna, GPT-5.6 Terra, GPT-5.6 Sol, Grok 4.5, Grok 4.6, MiniMax M3, MiMo-V2.5, Hy3, Claude Opus 5, Claude Fable 5, Claude Opus 4.8, Claude Opus 4.6, Claude Sonnet 4.6, Claude Sonnet 5, Claude Haiku 4.5, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, Gemini 3.5 Flash, Gemini 3.1 Pro Preview, Gemini 3 Pro Image, Gemini 3 Flash Preview, Gemini 3.1 Flash Lite and FLUX.2 Pro, served through one endpoint and one API key.
V4 Flash revision 0731 is the current agent build. It has 1M context and supports Chat Completions and Responses.
Up to 20% below the standard published per-token list rate, on most of the catalog. DeepSeek V4 Flash: $0.112 / $0.224. DeepSeek V4 Pro: $0.435 / $0.87. Kimi K3: $2.40 / $12.00. GLM 5.2: $1.12 / $3.52. Claude Opus 5: $4.00 / $20.00. GPT-5.6 Sol: $4.00 / $24.00. Grok 4.5: $1.60 / $4.80. Closed frontier models run through the same endpoint and the same key as the open-weight ones — Claude, GPT-5.6, Gemini and Grok included.
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, two ways. Every account gets a free trial balance to use in the browser chat at /chat — no card, no API key. And on your first credit purchase we match 100% of it, up to $50 in bonus credits: pay $5 and get $10, pay $50 and get $100. A larger first payment still receives the $50 maximum. One-time, applied automatically; standard pay-as-you-go after that.