Comparison
QuickSilver Pro vs OpenRouter
QuickSilver Pro sells Claude at 25% of Anthropic list price — Claude Opus 5.5 is 75% and Claude Sonnet 5.5 75% below OpenRouter's public per-token rates — and lists many open-weight models like Qwen 3.7 Plus and MiniMax M3 ~20% below. GPT-6.1 Sol and Grok 4.7 are at list price. Same OpenAI-compatible API, two-line migration. OpenRouter still wins on the long tail of community models.
At a glance
| Feature | QuickSilver Pro | OpenRouter |
|---|---|---|
| Models in catalog | 91 — GPT-6.1 Sol, Claude 5.5, Gemini 3.8, Grok 4.7, Qwen3.8, GLM-5.3, DeepSeek, Kimi K3.1 Pro, FLUX images | 300+ |
| Pricing on shared models | Claude 75% below; many open models ~20% below; GPT-6.1 Sol and Grok 4.7 at list | Baseline |
| OpenAI-compatible surface | Yes | Yes |
| Streaming / tools / json_schema | Yes — json_schema varies by model | Yes |
| usage.cost on responses | Yes (synthetic) | Yes |
| Per-key monthly spend limits | Yes | Yes |
| Closed frontier models (Claude, GPT-6.1, Gemini, Grok) | Yes — every Claude model 75% below (Opus 5.5 75%, Sonnet 5.5 75%), Gemini 15% below, GPT-6.1 and Grok at list | Yes |
| First top-up bonus | First top-up matched 100%, up to $50 (credited on your next top-up) | OpenRouterLimited free models |
| Minimum top-up | $5 | $10 |
Quick savings estimate
What do you spend on OpenRouter per month?
Lists only models below OpenRouter on both token legs (14 today); parity models add no savings.
Switch in 2 lines. $0.05 starter credit on starter models. No card.
Pricing (per million tokens, USD)
Competitor list prices, last checked 2026-09-30.
| Model | QSP input | QSP output | OpenRouter input | OpenRouter output | vs. list | QSP vs OpenRouter (OR) · in / out | |
|---|---|---|---|---|---|---|---|
| Claude Opus 5.5 | $1.00 | $5.00 | $4.00 | $20.00 | 75% | QSP $1.00 / $5.00 | OR $4.00 / $20.00 |
| Claude Sonnet 5.5 | $0.50 | $2.50 | $2.00 | $10.00 | 75% | QSP $0.50 / $2.50 | OR $2.00 / $10.00 |
| GLM-5.3 | $0.60 | $2.20 | $0.60 | $2.20 | at list | QSP $0.60 / $2.20 | OR $0.60 / $2.20 |
| Gemini 3.8 Flash | $0.6375 | $3.1875 | $0.75 | $3.75 | 15% | QSP $0.6375 / $3.1875 | OR $0.75 / $3.75 |
| Kimi K3 | $2.55 | $12.75 | $2.55 | $12.95 | compare token rates | QSP $2.55 / $12.75 | OR $2.55 / $12.95 |
| MiniMax M3 | $0.24 | $0.96 | $0.30 | $1.20 | 20% | QSP $0.24 / $0.96 | OR $0.30 / $1.20 |
| Qwen 3.7 Plus | $0.256 | $1.024 | $0.32 | $1.28 | 20% | QSP $0.256 / $1.024 | OR $0.32 / $1.28 |
| GPT-6.1 Sol | $2.00 | $10.00 | $2.00 | $10.00 | at list | QSP $2.00 / $10.00 | OR $2.00 / $10.00 |
QSP columns come from the live catalog at build time; OpenRouter columns are the published rates read on the date above.
Migration - two lines
Full migration guidefrom openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=os.environ["OPENROUTER_KEY"],
)
r = client.chat.completions.create(
model="deepseek/deepseek-v4-pro",
messages=[{"role": "user", "content": "Hi"}],
)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"}],
)The two changed lines are marked. Model IDs also change — see the 17 mappings in the guide.
FAQ
On many shared models, yes: Claude Opus 5.5 is 75% and Claude Sonnet 5.5 75% below OpenRouter's public per-token rates; Qwen 3.7 Plus, MiniMax M3 and MiMo V2.6 Pro ~20% below; Gemini 3.8 Flash ~15%. GPT-6.1 Sol and Grok 4.7 are at list price. Prices move — the table above has exact numbers as of October 2026.
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, z-ai/glm-5.3-flash -> glm-5.3-flash, openai/gpt-oss-120b -> gpt-oss-120b, qwen/qwen3.8-27b -> qwen3.8-27b, qwen/qwen3.8-flash -> qwen3.8-flash-next, qwen/qwen3.8-omni-flash -> qwen3.8-omni-flash and z-ai/glm-5.2 -> glm-5.2.
If your workload needs Llama, Mistral, or the long tail of community models. The closed frontier is here too — GPT-6.1 Sol, Claude Opus 5.5 and Sonnet 5.5, Gemini 3.8, Grok 4.7 — on one key, with Claude Opus 5.5 75% and Sonnet 5.5 75% below OpenRouter, and Gemini priced 15% under Google's own list.
Yes for the shared models. Streaming, tool / function calling, and standard usage accounting all work through the official OpenAI SDK, and each response returns a synthetic usage.cost computed from the public per-token rate. json_schema strict mode is model-dependent: the Claude models do not support it, so a schema there is advisory and the enforced path is a tool with strict: true.
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. The Qwen 3.6/3.7 models are served in non-thinking mode on QuickSilver Pro, so replies are direct; of these only Qwen 3.7 Max can opt back in, with enable_thinking: true.
Start with your own key
Change two lines. Compare current per-token prices before your first call.