- 1M context
- Reasoning
- Responses API
DeepSeek V4 Pro on QuickSilver Pro
DeepSeek V4 Pro is the V4 wave's flagship for premium reasoning — 1M-token context, reasoning by default, and an OpenAI-compatible Chat Completions and Responses API. QuickSilver Pro serves V4 Pro at $0.70 input / $2.10 output per million tokens — about 47% below DeepSeek's own published API price of $1.32 / $3.96. It is a cost-efficient alternative to o3-mini for long-context premium reasoning workloads.
- 1M context
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$0.70 / $2.10
47% lower
on both legs vs DeepSeek official list
Pricing comparison ($/1M tokens)
Bar length = price relative to the highest price shown
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.70 | $2.10 | lowest-cost |
| DeepSeek official list(DeepSeek official API) | $1.32 | $3.96 | 47% lower |
| OpenAI (o3-mini) | $1.10 | $4.40 | 52% lower |
DeepSeek list source: api-docs.deepseek.com/quick_start/pricing
At a glance
- Context
- 1M tokens
- Input / 1M
- $0.70
- Output / 1M
- $2.10
- Thinks by default
- Yes
- Latency · live
- —
- AA Intelligence Index
- 42
Premium reasoning + 1M context, at ~47% below DeepSeek’s own published API price.
When is DeepSeek V4 Pro the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
V4 Pro is the right pick when V4 Flash isn't smart enough but frontier-tier per-token costs start adding up. Multi-step coding agents, refactor planners, large-document summarization with reasoning, competition-math / theorem-style problems, and any workload where you'd consider o3-mini but the price is the blocker. The 1M context window scales further than o3-mini's 200K.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Multi-step reasoning, on by default
- Responses API clients as well as Chat Completions
When to use something else
For routine chat, codegen, or non-agentic single-shot tasks, V4 Flash ($0.06/$0.18) lands most of them for less. For closed-model capabilities, stay on OpenAI's o-series. For agentic / planning at Opus class, Kimi K2.6.
Quickstart (curl)
Get an API key →curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.quicksilverpro.io/v1",
apiKey: process.env.QSP_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek-v4-pro",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.quicksilverpro.io/v1/responses \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"input": "Hello!"
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="deepseek-v4-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)OpenAI-compatible. One-line migration via base_url.
Gateway behavior
Compatibility notes for this model.
prompt- Prompts up to 1M tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Not listed for this model
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- $1.32 / $3.96api-docs.deepseek.com/quick_start/pricing
- Catalog verified
- Prompt cache · not compared
- $0.10 read
usage.cost = prompt_tokens × $0.70/1M + completion_tokens × $2.10/1M
FAQ
Common questions
On premium-reasoning workloads with long context, it can be. V4 Pro reasons by default, supports 1M context versus o3-mini's 200K, and lists at $0.70 input / $2.10 output versus o3-mini's $1.10 / $4.40 per million tokens. Match both on your own eval set; V4 Pro is text-only, while 45 of our 91 models accept image input.
V4 Pro is the premium reasoning tier of the V4 wave — deeper chain-of-thought on hard problems (competition math, theorem proving, multi-step planning) at $0.70 / $2.10 per 1M. V4 Flash ($0.06/$0.18) is the low-cost workhorse for routine chat and codegen. Both carry catalog-derived context limits and think by default. Reach for V4 Pro when the answer quality on hard reasoning matters more than the per-token cost.
Roughly, yes — 1M tokens is about 2.5–3 million words of code in modern languages. That's enough for most monorepos. Keep in mind cost scales linearly with input tokens (~$0.70 per 1M input), so dumping a 1M-token context costs $0.70 just on input before reasoning. For frequently-repeated context, consider RAG or partial-prompt caching when we ship it.
QuickSilver Pro charges $0.70 per million input tokens, $2.10 per million output tokens, and $0.10 per million cached-input tokens — about 47% below DeepSeek's own published API list of $1.32 / $3.96 per million tokens.