tencent logo
tencent

Tencent: Hy4 flash

Source description (English)

Hy4 flash is a cost-efficient variant of Hy4 from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...

Overview

Model specifications

Context
1,048,576 tokens
Maximum output
65,536 tokens
Architecture
text+image->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.035
per 1M tokens
Output
$0.1405
per 1M tokens
Cache read
$0.0015
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
No
Default parameters
Yes
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tencent/hy4-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
text
Reasoning

Yes

API

Supported API parameters

include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetools
Available providers

1 Provider

Checked: November 19, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Tencent

fp8
Context
1.0M
Maximum output
66K
Input
$0.035
Output
$0.1405
Cache read
$0.0015
Cache write
Not provided
tencent

4 models

All models