- 1M context
- Multimodal
- Responses API
Qwen3.7 Flash on QuickSilver Pro
Qwen 3.7 Flash is Alibaba's fast multimodal agent model for visual coding, search, computer interaction, and high-volume automation. It supports text and image input over a 1M-token context. QuickSilver Pro serves it at $0.024 input / $0.104 output per million tokens — 20% below OpenRouter.
- 1M context
- Vision
- Tools
- Streaming
- JSON Schema output
You pay · input / output per 1M
$0.024 / $0.104
20% lower
on both legs vs OpenRouter
Pricing comparison ($/1M tokens)
Bar length = price relative to the highest price shown
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.024 | $0.104 | lowest-cost |
| OpenRouter(qwen/qwen3.7-flash) | $0.03 | $0.13 | 20% lower |
| OpenAI (GPT-4o mini) | $0.15 | $0.60 | 83% lower |
OpenRouter list source: openrouter.ai/qwen/qwen3.7-flash
At a glance
- Context
- 1M tokens
- Input / 1M
- $0.024
- Output / 1M
- $0.104
- Thinks by default
- No
- Latency · live
- —
Fast multimodal agents, visual coding, search, and high-volume automation over a 1M context.
When is Qwen3.7 Flash the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Use Qwen 3.7 Flash for high-volume multimodal chat, visual coding, screenshot and document understanding, search agents, tool use, and computer-interaction workflows where latency and price matter. QuickSilver Pro serves it in non-thinking mode for fast, predictable output.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Responses API clients as well as Chat Completions
When to use something else
For the hardest reasoning, step up to Qwen 3.7 Max or DeepSeek V4 Pro. For long-running coding loops where quality matters more than the lowest possible token price, compare Qwen 3.7 Plus.
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": "qwen3.7-flash",
"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="qwen3.7-flash",
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: "qwen3.7-flash",
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": "qwen3.7-flash",
"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="qwen3.7-flash",
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: Supported
- JSON Schema: Supported
- reasoning: Not listed for this model
Where the price comes from
- Provider reference
- $0.03 / $0.13openrouter.ai/qwen/qwen3.7-flash
- Catalog verified
- Prompt cache · not compared
- $0.0048 read
usage.cost = prompt_tokens × $0.024/1M + completion_tokens × $0.104/1M
FAQ
Common questions
No. QuickSilver Pro serves it in non-thinking mode for fast direct answers, and a reasoning field in the request does not turn thinking on. For a reasoning trace in the Qwen family, use Qwen 3.7 Max with enable_thinking=true.
The current route supports text and image input, text output, tool calling, and a 1M-token context. It is designed for multimodal agents, visual coding, search, and computer interaction.
OpenRouter lists Qwen 3.7 Flash at $0.03 input / $0.13 output per 1M tokens. QuickSilver Pro is $0.024 / $0.104 — 20% below on both legs, with the model ID shortened to qwen3.7-flash.