Comparison
QuickSilver Pro vs Google Vertex AI
Vertex AI is GCP's managed inference plane: Gemini, Claude on Vertex, Llama, plus a Model Garden of open weights. It's the right tool when GCP-native integration (IAM, BigQuery sources, Vertex Search) is load-bearing. For everyone else, QuickSilver Pro serves DeepSeek V4 Flash + Pro, Qwen 3.7 Max + 3.6 Plus + 3.6, and Kimi K2.6 through a plain OpenAI-compatible API — no GCP project, no service-account JSON, no quota requests.
At a glance
| Feature | QuickSilver Pro | Vertex AI |
|---|---|---|
| Model focus | Open weights + closed frontier (GPT-6.1, Claude, Gemini, Grok, Qwen, GLM, DeepSeek, Kimi) | Vertex AIGemini family, Claude on Vertex, Llama, Mistral, Model Garden |
| API surface | OpenAI-compatible (drop-in) | Vertex AIVertex SDK / REST with GCP auth |
| DeepSeek V4 Pro output | $2.10 / 1M | Vertex AIn/a (not in Model Garden as of 2026) |
| DeepSeek V4 Flash output | $0.18 / 1M | Vertex AIvaries by Model Garden host |
| GCP IAM + Private Service Connect | No | Yes |
| Vertex Search / Vector Search | No | Yes |
| Setup | Sign up, paste key | Vertex AIGCP project + quota + service account |
Pricing (per million tokens, USD)
Competitor list prices as published by each provider.No check date
| Model | QSP input | QSP output | Vertex AI input | Vertex AI output | vs. list | QSP vs Vertex AI (Vertex) · in / out | |
|---|---|---|---|---|---|---|---|
| deepseek-v4-flash vs gemini-2.0-flash | $0.06 | $0.18 | $0.075 | $0.30 | V4 Flash lower on both legs | QSP $0.06 / $0.18 | Vertex $0.075 / $0.30 |
| deepseek-v4-pro vs gemini-2.0-pro | $0.70 | $2.10 | $1.25 | $5.00 | ~2.4x output | QSP $0.70 / $2.10 | Vertex $1.25 / $5.00 |
| qwen3.6-35b vs gemini-2.0-flash | $0.05 | $0.70 | $0.075 | $0.30 | Gemini lower, Qwen has 262K context | QSP $0.05 / $0.70 | Vertex $0.075 / $0.30 |
QSP columns come from the live catalog at build time; Vertex AI columns are the rates Vertex AI publishes. No check date is recorded for them.
Migration - two lines
import os
from openai import OpenAI
# Was: aiplatform.init(project=..., location=...); GenerativeModel(...)
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
r = client.chat.completions.create(
model="deepseek-v4-pro", # or qwen3.8-flash-next for long-context RAG
messages=[{"role": "user", "content": "Hi"}],
)The two changed lines are marked.
FAQ
For pure-price low-cost chat, Gemini 2.0 Flash costs less than V4 Flash on input ($0.075 vs $0.06) but more expensive on output ($0.30 vs $0.18). For premium reasoning against Gemini 2.0 Pro, DeepSeek V4 Pro is ~2.4× lower on output ($2.10 vs $5.00). The open-source vs closed quality gap on text-only tasks is small for most production workloads.
No — Vertex's SDK is GCP-shaped (project / location / publisher / model / endpoint). Use the openai SDK with base_url=https://api.quicksilverpro.io/v1 and a QSP key. Migration is typically one file: the OpenAI shape covers streaming, tool calling, structured output (json_schema where the model supports it — the Claude models do not) and usage accounting without GCP IAM setup.
When GCP IAM, Private Service Connect, BigQuery-as-source RAG, Vertex Search, or sovereign-cloud regions are non-negotiable. Also when you need Gemini's video or audio modalities, or Claude on Vertex for the same procurement reason — image input we already serve on 48 models. QSP is for the chat / coding / reasoning slice where open-source DeepSeek / Qwen is quality-equivalent.
No. QuickSilver Pro is a curated catalog focused on the highest-quality open-source LLMs at the lowest sustainable per-token price. We don't offer per-customer fine-tunes or embeddings, though Nano Banana Pro (Gemini 3 Pro Image), Nano Banana 2.1, FLUX.2 Pro, FLUX.1 Schnell, SDXL Turbo, FLUX.2 Klein, Qwen Image 3.0, Seedream 5.0 Pro, Seedream 4, Bria FIBO 1.5, Bria FIBO 2.0, GPT Image 2, GPT Image 2.5 Flare and GPT Image 2.5 Sunburst generate images. Vertex's Model Garden is broader; QSP is deeper on a smaller surface.
Start with your own key
Change two lines. Compare current per-token prices before your first call.