Hy4 Flash

tencent/hy4-flash
NewFeaturedZDR
VisionToolsJSONReasoning
by Tencent · 2026-11-16

Hy4 flash is the cost-efficient variant of Tencent Hunyuan Hy4, served with roughly a quarter of the flagship parameter count for markedly lower latency and cost. It keeps the 1M-token context window and accepts text and image input with text output, generating up to 64K output tokens. It targets code assistance, agentic tool-use, and high-volume productivity workloads where throughput and price matter more than peak reasoning depth. Thinking is enabled by default, and it supports native tool calling, structured outputs, and the chat completions, Responses, and Anthropic Messages APIs. Unlike the flagship Hy4, the flash variant does not expose selectable reasoning-effort levels.

ctx1M tokens
Max output65K
Inputtext + image
Outputtext
p50 TTFT1.88 s
Data retentionZero Data Retention available. With ZDR on, requests go only to providers with a zero-retention agreement.
Runs inEuropean Union
INPUT$0.02/ 1M tokens
OUTPUT$0.07/ 1M tokens
p50 TTFT1.88 s7d
p95 TTFT1.88 s7d
TRAFFICCollecting…

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
  • Anthropic SDKhttps://api.orcarouter.ai
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="tencent/hy4-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools

Pricing

Pricing
Input / 1M tokens$0.018
Output / 1M tokens$0.070
Cache read / 1M$0.0008
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $0.333 · With prompt caching $0.275

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000035

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.88 s
Output speed
Collecting…
p95 TTFT
1.88 s
Error rate
Collecting…

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News4 mentions · 7dup 4 vs the previous week

How it compares

Hy4 FlashHy3Hy4 previewHy4
Input $/M$0.02$0.18$0.83$0.83
Output $/M$0.07$0.59$2.50$2.50
Context1.0M262K1.0M1.0M
Quality6/108/108/107/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

How much does Tencent: Hy4 Flash cost on OrcaRouter?
Tencent: Hy4 Flash is priced at $0.02 per 1M input tokens and $0.07 per 1M output tokens via OrcaRouter. Pricing is pulled live from the routing layer.
What is Tencent: Hy4 Flash's context window?
Tencent: Hy4 Flash supports a context window of 1M tokens. Use long-context features (RAG, summarisation) up to that limit.
How do I call Tencent: Hy4 Flash via the OpenAI SDK?
Set OpenAI base_url to https://api.orcarouter.ai/v1, supply your OrcaRouter API key, and pass model="tencent/hy4-flash" in the chat.completions.create call.
Does OrcaRouter rate-limit Tencent: Hy4 Flash?
Per-model rate limits follow your OrcaRouter plan. Free tiers ship with conservative caps; paid tiers lift them. Check /pricing for current quotas.

Embed this badge

Tencent: Hy4 Flash•$0.02/M in•1884ms p50•via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/tencent/hy4-flash" target="_blank"> <img src="https://www.orcarouter.ai/embed/tencent/hy4-flash.svg" alt="Tencent: Hy4 Flash on OrcaRouter" /> </a>
Markdown [![Tencent: Hy4 Flash](https://www.orcarouter.ai/embed/tencent/hy4-flash.svg)](https://www.orcarouter.ai/models/tencent/hy4-flash)

Model card as data

GET /api/public/models/tencent/hy4-flashOpen
Machine-readable:/llms.txt/llms-full.txt