QuickSilver Pro vs OpenRouter
QuickSilver Pro lists most shared models at ~20% below OpenRouter's public per-token rates — open weights like Kimi K3, DeepSeek V4 Flash + Pro and Qwen 3.7 Plus, and closed frontier models like Claude Opus 5, GPT-5.6 and Grok 4.5. Same OpenAI-compatible API, two-line migration. Qwen 3.7 Max is the exception: Alibaba is its only provider, so we sell it at parity. OpenRouter still wins on the long tail of community models.
At a glance
| Feature | QuickSilver Pro | openrouter |
|---|---|---|
| Models in catalog | 40 — Kimi K3, DeepSeek V4, GLM 5.3, Qwen 3.7, Nemotron, Claude, GPT-5.6, Gemini, Grok | 300+ |
| Pricing on shared models | 20% below OpenRouter on most | Baseline |
| OpenAI-compatible surface | Yes | Yes |
| Streaming / tools / json_schema | Yes | Yes |
| usage.cost on responses | Yes (synthetic) | Yes |
| Per-key monthly spend limits | Yes | Yes |
| Closed frontier models (Claude, GPT-5.6, Gemini, Grok) | Yes — 20% below | Yes |
| Launch bonus | First deposit matched 100%, up to $50 | Limited free models |
| Minimum top-up | $5 | $10 |
Pricing (per million tokens, USD)
Competitor list prices, last checked 2026-08-04.
| Model | QSP input | QSP output | openrouter input | openrouter output | vs. list |
|---|---|---|---|---|---|
| DeepSeek V4 Flash | $0.112 | $0.224 | $0.14 | $0.28 | 20% |
| DeepSeek V4 Pro | $0.435 | $0.87 | $0.435 | $0.87 | ~20% |
| Qwen3.6-35B-A3B | $0.112 | $0.80 | $0.14 | $1.00 | ~20% |
| Kimi K3 | $2.40 | $12.00 | $3.00 | $15.00 | ~20% |
| Claude Opus 5 | $4.00 | $20.00 | $5.00 | $25.00 | ~20% |
| Kimi K2.6 | $0.5472 | $2.728 | $0.589 | $2.48 | mixed by leg |
Migration - two lines
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
r = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hi"}],
)FAQ
Yes, on most shared models (Kimi K3, DeepSeek V4 Flash + Pro, Qwen 3.7 Plus, Claude Opus 5, GPT-5.6, Grok 4.5): ~20% below OpenRouter's public per-token rates. Qwen 3.7 Max is ~15% below because we buy it straight from Alibaba, its only provider. See the pricing table above for exact numbers.
Two lines in your OpenAI SDK setup: change base_url from openrouter.ai/api/v1 to api.quicksilverpro.io/v1 and swap the API key. Model ID mappings: deepseek/deepseek-v4-flash-0731 -> deepseek-v4-flash, deepseek/deepseek-v4-pro -> deepseek-v4-pro, qwen/qwen3.7-max -> qwen3.7-max, qwen/qwen3.7-plus -> qwen3.7-plus, qwen/qwen3.7-flash -> qwen3.7-flash, qwen/qwen3.6-plus -> qwen3.6-plus, qwen/qwen3.6-35b-a3b -> qwen3.6-35b, moonshotai/kimi-k2.6 -> kimi-k2.6, moonshotai/kimi-k2.7-code -> kimi-k2.7-code, moonshotai/kimi-k3 -> kimi-k3, z-ai/glm-5.3 -> glm-5.3 and z-ai/glm-5.2 -> glm-5.2.
If your workload needs Llama, Mistral, or the long tail of community models. Claude, GPT-5.6 and Grok are all on QuickSilver Pro at 20% below OpenRouter (Gemini is here too, priced against Google's own list), so closed frontier models are no longer a reason to stay.
Yes for the shared models. Streaming, tool / function calling, json_schema strict mode, and standard usage accounting all work through the official OpenAI SDK. Each response also returns a synthetic usage.cost computed from the public per-token rate.
DeepSeek V4 Flash + Pro, Qwen 3.6/3.7, and Kimi K2.6 all default to chain-of-thought reasoning on OpenRouter — so a one-token "Hi" can return hundreds of reasoning tokens. For DeepSeek V4 and Kimi K2.6 we pass requests through unchanged: set `reasoning: { enabled: false }` to get non-thinking low-cost chat without the thinking overhead. For the Qwen 3.6/3.7 models the gateway already sends `reasoning: { enabled: false }` by default — pass `reasoning: { enabled: true }` to opt back into reasoning.