Tencent: Hy4 preview

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.

Source-linked Hy Open weights Released 2026-08-28

API record Report

InputT

OutputT

Input price$0.67/M

Output price$2/M

Context1.024M

Max output64K

Providers9

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Hy4 preview
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Vancine	`hy4-preview`	1.024M	64K	$0.67	$2	$0.034	ReasoningTools	Docs ↗
Kilo Gateway	`tencent/hy4-preview`	1.04858M	64K	$0.834	$2.501	$0.042	ReasoningToolsJSON	Docs ↗
OpenCode Go	`hy4-preview`	1.024M	64K	$0.834	$2.501	$0.042	ReasoningTools	Docs ↗
OpenRouter	`tencent/hy4-preview`	1.04858M	64K	$0.834	$2.501	$0.042	ReasoningToolsJSON	Docs ↗
Tencent TokenHub	`hy4-preview`	1.024M	64K	$0.834	$2.501	$0.042	ReasoningTools	Docs ↗
Tencent Token Plan	`hy4-preview`	1.024M	64K	$0.834	$2.501	$0.042	ReasoningTools	Docs ↗
Vercel AI Gateway	`tencent/hy4-preview`	1.024M	64K	$0.834	$2.501	$0.042	ReasoningTools	Docs ↗
NanoGPT	`tencent/hy4-preview`	1.04858M	64K	$0.834	$2.501	$0.042	ReasoningToolsJSON	Docs ↗
CrossModel	`tencent/hy4-preview`	1.04858M	65.536K	$0.96	$2.88	$0.048	ReasoningTools	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.67/M

Across 9 priced providers

Median input $0.834/M

Midpoint of listed rates

Highest input $0.96/M

1.4× the lowest listed rate

Output range $2 – $2.88

Per million output tokens

Vancine $0.67/MLowest

Kilo Gateway $0.834/M

OpenCode Go $0.834/M

OpenRouter $0.834/M

Tencent TokenHub $0.834/M

Tencent Token Plan $0.834/M

Vercel AI Gateway $0.834/M

NanoGPT $0.834/M

CrossModel $0.96/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 1.024M to 1.04858M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes

✓ Tool calling Yes

✓ Structured output Yes

× Attachments No

× Vision input No

✓ Open weights Yes

Creator: Tencent
Model family: Hy
Knowledge cutoff: Not documented
License: Not documented
Release date: 2026-08-28
Model ID: tencent/hy4-preview

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Sep 11, 2026Context Length1048576 → 1024000

Sep 11, 2026Price Completion2.501 → 2.0

Sep 11, 2026Price Prompt0.834 → 0.67

Sep 11, 2026Price Completion2.0 → 2.501

Sep 11, 2026Context Length1024000 → 1048576

Sep 11, 2026Price Prompt0.67 → 0.834

Sep 11, 2026Context Length1048576 → 1024000

Sep 11, 2026Price Completion2.501 → 2.0

Sep 11, 2026Price Prompt0.834 → 0.67

Sep 11, 2026Context Length1024000 → 1048576

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Models.devcatalog ↗Vancine documentationprovider documentation ↗Kilo Gateway documentationprovider documentation ↗OpenCode Go documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Tencent TokenHub documentationprovider documentation ↗Tencent Token Plan documentationprovider documentation ↗Vercel AI Gateway documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗CrossModel documentationprovider documentation ↗

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/tencent/hy4-preview

curl

curl "https://model.kyssta.lol/api/v1/models/tencent/hy4-preview"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Hy4 preview?

A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities. It is published by Tencent and catalogued here from Models.dev.

How much does Hy4 preview cost?

Listed input pricing starts at $0.67 per million tokens from Vancine, rising to $0.96 across 9 listed providers.

What is the context length of Hy4 preview?

Hy4 preview accepts up to 1.024M tokens of context and returns up to 64K output tokens.

Does Hy4 preview support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, and reasoning.

Which providers serve Hy4 preview?

9 providers list this model: Vancine, Kilo Gateway, OpenCode Go, OpenRouter, Tencent TokenHub, Tencent Token Plan and 3 more.

Are the weights for Hy4 preview open?

Yes. The weights are published.

When was Hy4 preview released?

The catalog records a release date of 2026-08-28, last verified Sep 11, 2026.

More models from Tencent

View all →

Tencent: Hy-MT2-7B

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

8.192K ctx $0.074/M in Hy3

Tencent Hy reasoning model for coding, instruction following, and agent tasks

256K ctx $0.066/M in Tencent: Hy-MT2-30B-A3B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

8.192K ctx $0.074/M in deepseek-v4-pro

No provider description available.

1M ctx $0.435/M in