Home › Models › Hy4 Flash
Tencent · 1M Context

Hy4 Flash API

Tencent Hunyuan hy4-flash is the cost-efficient flash variant of the hy4 generation — 1M context, strong CN & agentic reasoning. Priced at provider list rates, aligned to OpenRouter ($0.035 / $0.1405 per 1M).

$0.035
Input / 1M tokens
$0.1405
Output / 1M tokens
1M
Context window
Reasoning
Flash tier
Sign Up - Get $2.00 Free Credit See All Pricing

Why use Hy4 Flash on NovAI?

  • Cost-efficient hy4 flash tier — roughly 1/3 the input price of hy4
  • 1M-token context window
  • Strong Chinese reasoning & agent tool use
  • Aligned to OpenRouter ($0.035 / $0.1405 per 1M)
  • Zero platform fee

Best use cases

  • Long-document and repo-scale reasoning
  • Complex multi-step agents
  • Research, analysis & synthesis
  • Advanced coding and refactoring

Quick start

Cost-efficient hy4 flash tier

cURL

curl https://aiapi-pro.com/v1/chat/completions \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy4-flash",
    "messages": [{"role":"user","content":"Draft a release note from these bullet points."}]
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.chat.completions.create(
    model="hy4-flash",
    messages=[{"role":"user","content":"Draft a release note from these bullet points."}],
)
print(resp.choices[0].message.content)

Try Hy4 Flash today

Zero platform fee. Credits never expire. OpenAI-compatible API.

Sign Up FreeTop Up +25% Bonus