- 1M context
- Multimodal
- Reasoning
- Responses API
- NEW · Nov 4
Hy4 on QuickSilver Pro
Hy4 is Tencent's general-availability model for reasoning and agentic coding, with text and image input over a 1M-token context. Pricing is $0.459 input / $1.375 output per 1M tokens.
- 1M context
- 66K max output
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$0.459 / $1.375
10% more expensive
on both legs vs OpenRouter
Pricing comparison ($/1M tokens)
Bar length = price relative to the highest price shown
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.459 | $1.375 | — |
| OpenRouter(tencent/hy4) | $0.417 | $1.2505 | 10% more expensive |
Tencent list source: openrouter.ai/tencent/hy4
At a glance
- Context
- 1M tokens
- Input / 1M
- $0.459
- Output / 1M
- $1.375
- Thinks by default
- Yes
- Max output
- 66K
- Latency · live
- —
Multimodal reasoning and agentic coding over a 1M-token context.
When is Hy4 the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Choose Hy4 for long-context code review, image-assisted analysis, and agents using automatic tool selection.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Multi-step reasoning, on by default
When to use something else
Forced named functions and required tool selection are unsupported. Temperature is supported; top_p is dropped. Reasoning is available; this page does not promise a per-request reasoning toggle.
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": "hy4",
"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="hy4",
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: "hy4",
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": "hy4",
"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="hy4",
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.
top_p- top_p is dropped; temperature is retained.
prompt- Prompts up to 1M tokens.
max_tokens- Up to 66K output tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Supported
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- $0.417 / $1.2505openrouter.ai/tencent/hy4
- Catalog verified
- Prompt cache · not compared
- $0.0231 read
usage.cost = prompt_tokens × $0.459/1M + completion_tokens × $1.375/1M
FAQ
Common questions
Tencent's general-availability Hy4, released November 4, 2026. Endpoint metadata lists 1M context tokens, 65,536 maximum output tokens, image input, reasoning, tools and structured output. Hy4 Preview remains available separately.
Use base_url=https://api.quicksilverpro.io/v1 and model="hy4" with your QSP key. Chat Completions and Responses are supported by the gateway. Tool choice supports auto and none; forced named and required choices are unsupported. Endpoint metadata lists these model features.
$0.459 input / $1.375 output per 1M tokens, with cached input at $0.0231 per 1M tokens. No cache-write price is listed.