How much does Hy4 preview cost?

Hy4 preview costs $0.7506/M input tokens and $2.251/M output tokens, with separate rates for Cache Read at $0.0378/M tokens.

What is the context length of Hy4 preview?

Hy4 preview has a 1,048,576 token context window. It supports up to 64,000 completion tokens.

Does Hy4 preview support tool calling and structured outputs?

Yes. Hy4 preview accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Which providers serve Hy4 preview?

Hy4 preview is served by 6 providers on OpenRouter: Tencent Cloud, GMICloud, AtlasCloud, DeepInfra, NovitaAI, and SiliconFlow. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Hy4 preview released?

Hy4 preview was released on August 28, 2026.

Tencent: Hy4 preview

tencent/hy4-preview

Model weights

Compare

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.

Modalities

In / out price

$0.7506 / $2.251per 1M

Context

1.0M

Released

Aug 28, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


$0.834	$2.501	$0.042	1.16s	64 tok/s	100.00%
$0.834$0.7506	$2.501$2.2509	$0.042$0.0378	3.53s	42 tok/s	100.00%
$0.834	$2.501	$0.042	1.00s	61 tok/s	99.91%
$0.834	$2.501	$0.042	1.88s	29 tok/s	99.44%
$0.834	$2.501	$0.042	3.01s	37 tok/s	100.00%
$0.834	$2.501	$0.042	1.77s	52 tok/s	100.00%

Input $0.834Output $2.501
64 tok/s100.00% uptime
Input $0.7506Output $2.2509
42 tok/s100.00% uptime
Input $0.834Output $2.501
61 tok/s99.91% uptime
Input $0.834Output $2.501
29 tok/s99.44% uptime
Input $0.834Output $2.501
37 tok/s100.00% uptime
Input $0.834Output $2.501
52 tok/s100.00% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.07658/M tokens

Output

$2.486/M tokens

Hy4 preview — Price history

Price history

No effective price data for this selection

$0.0678	$2.50	96.7%	16.9%
$0.0747	$2.47	95.7%	74.5%
$0.0953	$2.50	93.3%	5.6%
$0.1117	$2.50	91.2%	1.5%
$0.1709	$2.50	83.7%	0.8%
$0.1966	$2.50	80.5%	0.7%

Effective in $0.0678Effective out $2.50
Token share
16.9%
Effective in $0.0747Effective out $2.47
Token share
74.5%
Effective in $0.0953Effective out $2.50
Token share
5.6%
Effective in $0.1117Effective out $2.50
Token share
1.5%
Effective in $0.1709Effective out $2.50
Token share
0.8%
Effective in $0.1966Effective out $2.50
Token share
0.7%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

64tok/s

P50, best across providers

Latency

1.00s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchDeepInfra90.5%77.1%auto-routing89.7%76.7%Cohere90.0%76.0%NovitaAI89.2%76.6%GMICloud89.4%76.2%

+4 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

99.90%

Availability over the last 3 days

Last 72 hours

Availability 99.90%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.81%

Without Routing

98.66%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Tencent: Hy4 preview (Vals AI)
Source	Benchmark	Score
Vals AI	Hy4 Preview BioMysteryBench	69.3%
Vals AI	Hy4 Preview Code Migration v1.1	45.4%
Vals AI	Hy4 Preview CyberBench v1.1	65.4%
Vals AI	Hy4 Preview EMB v1.1	68.9%
Vals AI	Hy4 Preview Finance Agent v2.1	61.6%
Vals AI	Hy4 Preview Vals Finance Index	57.5%
Vals AI	Hy4 Preview HLAB-Vals-1.1	8.8%
Vals AI	Hy4 Preview IOI	59.3%
Vals AI	Hy4 Preview LegalBench	83.8%
Vals AI	Hy4 Preview Vals Legal Index	71.7%
Vals AI	Hy4 Preview Legal Research Bench	45.2%
Vals AI	Hy4 Preview MedCode	43.2%
Vals AI	Hy4 Preview MedScribe	83.6%
Vals AI	Hy4 Preview ProgramBench	0.0%
Vals AI	Hy4 Preview ProofBench v1.1	75.0%
Vals AI	Hy4 Preview Public Benefits Bench v1.1	68.6%
Vals AI	Hy4 Preview SRE Bench	2.3%
Vals AI	Hy4 Preview Tax Agent Bench	32.6%
Vals AI	Hy4 Preview Terminal-Bench 4.0	8.1%
Vals AI	Hy4 Preview Terminal-Bench-Science	1.4%
Vals AI	Hy4 Preview Vals Index	53.2%
Vals AI	Hy4 Preview Vibe Code Bench v1.1	77.5%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

1.88Ttokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

40.6Btokens

Portkey AI

Control panel for AI apps

15.4Btokens

One API

AI key management system

7Btokens

Codex

A coding agent that helps you build and ship with AI

2.68Btokens

Top 5 Apps

4.88B

Rest of OpenRouter

1.6B

Not currently available through EU in-region routing. In-region routing docs

More models from tencent

HY-World 2.1 Panorama

HY-World 2.1 Panorama is a 360-degree panorama generation model from Tencent, part of the Hunyuan World family. It turns a single text prompt into one high-resolution equirectangular panorama suitable for virtual tours, skyboxes, and world-building, and is particularly strong at coherent, seamless scene layout across the full sphere. Each request produces one panorama; prompts are capped at 600 characters.

Image$1.60/M tokens

Hy4

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for the first time.

Text1.0M context$0.417 / $1.251

Hy Image 3.5 Preview

Hy Image 3.5 Preview is a unified image generation and editing model from Tencent. It handles text-to-image, image-to-image, and multi-turn editing through one endpoint, taking up to 20 reference images per request and producing output up to 4K. Built on the 80B mixture-of-experts Hy Image 3.0 base, it is particularly strong at subject consistency across edits, prompt-faithful composition, and rendering Chinese and English text inside images.

Image$1.60/M tokens

Hy-MT2-1.8B

Hy-MT2-1.8B is a compact 1.8B-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.

Text8K context$0.044 / $0.177

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 style-guided translation. It uses 3B active parameters out of 30B total.

Text8K context$0.074 / $0.295

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.

Text8K context$0.074 / $0.295

Hy3

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.

Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.

Text262K context$0.0825 / $0.33

Hy3 preview

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering strong code generation and reliable performance across multi-step, real-world workflows.

Text262K context$0.18 / $0.60

Hunyuan A13B Instruct

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).

Text131K context$0.14 / $0.57

Tencent: Hy4 preview

Providers