vakati-tech.ai

// tencent

Hy4 flash

tencent/hy4-flash

newreasoningtool callingimage inputprompt caching

Hy4 flash costs $0.035 per 1M input tokens and $0.140 per 1M output tokens with a 1.0M-token context window.

A reasoning, tool-calling model from tencent, released Nov 16, 2026. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.

Input / 1M
$0.035
Output / 1M
$0.140
Context
1.0M
LiveBench overall
Not evaluated

Specs and pricing

Input price

USD per 1M prompt tokens

$0.035
Output price

USD per 1M completion tokens, reasoning included

$0.140
Blended price

3:1 input:output — #22 cheapest of 350 listed models

$0.061
Cached input read

Blank means not priced separately — not free

$0.0015
Cache write—
Context window1,048,576 tokens
Max output65,536 tokens
Input modalitiestext, image
Tool callingYes
Extended reasoningYes
Knowledge cutoff—
ListedNov 16, 2026
All Tencent API pricing

What Hy4 flash costs to run

Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.

WorkloadPer month
Support chatbot

1.2K in / 400 out × 200K requests

$17.23/mo
RAG assistant

8K in / 600 out × 100K requests

$23.03/mo
Coding agent

40K in / 4K out × 20K requests

$20.48/mo
Document extraction

20K in / 1.5K out × 50K requests

$43.86/mo
Bulk classification

500 in / 20 out × 5M requests

$84.80/mo
Price your own workload

Compare Hy4 flash with

Benchmarked models at a similar price.

Cheaper and stronger alternatives to Hy4 flash

Hy4 flash FAQ

How much does Hy4 flash cost?

Hy4 flash lists at $0.035 per 1M input tokens and $0.140 per 1M output tokens, with cached input reads at $0.0015 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $23.03 at list price.

What is the context window of Hy4 flash?

Hy4 flash accepts up to 1,048,576 tokens of context and can return up to 65,536 output tokens per response.

Does Hy4 flash support tool calling?

Yes — Hy4 flash supports tool (function) calling and exposes extended reasoning. It accepts text, image input.

How does Hy4 flash score on benchmarks?

LiveBench has not published a run for Hy4 flash yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.

What is the API model ID for Hy4 flash?

On OpenRouter the model ID is "tencent/hy4-flash". It was listed on Nov 16, 2026.

More from tencent

How these numbers are produced

  • Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
  • Scores and ranks — LiveBench release 2026-11-06. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
  • Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.

Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.