Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Tencent / Hunyuan Vision

HY-Vision-2.0-Instruct

Vision-language model for image questions, visual grounding, charts and document content.

Language models (LLMs)
availableClosed weightsText generationVision
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
6 of 18 specification fields collected
Input token limit24KSee specification notes below
Maximum output16KSee specification notes below
Input billingSee ratesTencent TokenHub
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
44KSource for Context / input limit (opens in a new tab)

Published context and input/output limits are separate constraints. K is retained as documented.

Maximum output
16KSource for Maximum output (opens in a new tab)

Published context and input/output limits are separate constraints. K is retained as documented.

Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

No model-specific cache eligibility or cache discount was verified. A shared gateway field or usage counter does not establish support.

Maximum input tokens
24KSource for Maximum input tokens (opens in a new tab)

Published context and input/output limits are separate constraints. K is retained as documented.

Input image limits
JPEG/PNG/GIF/WebP. HY-Vision image count is constrained by the context window; no fixed image-count limit is stated.Source for Input image limits (opens in a new tab)

The guide describes common file-size guidance separately and notes model-specific limits may differ.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Tencent TokenHub

Provider source (opens in a new tab)
API model ID
hy-vision-2.0-instruct
Access
Tencent Cloud account, activated model service and TokenHub API key required. Availability is documented, not confirmed by a paid inference call.
Regions
Guangzhou gateway. Availability on the separate Singapore site is not inferred; site API keys are not interchangeable.
API endpoint URL
POST https://tokenhub.tencentmaas.com/v1/chat/completionsSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text token inferenceInput1CN¥7.501 million tokens
Text token inferenceOutput1CN¥17.501 million tokens

Rate conditions

  1. Published Guangzhou TokenHub rate in CNY. Input and output are separate charges. No currency conversion, cache discount or batch discount has been assumed.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Tencent TokenHub

hy-vision-2.0-instruct
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
The platform cache guide does not establish this model’s eligibility, TTL or discount.Source for Limits & data boundaries (opens in a new tab)

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred for this named native commercial model service from its official access documentation and comparison with Tencent’s published model-weight inventory. No weight release for this exact service was found in the reviewed inventory. This is not a claim that every Tencent model is closed or that the provider has disclosed the underlying checkpoint. Public Hy3, Hy4, Hy-MT2 and HunyuanImage 3.0 releases are excluded.

Classification evidence (opens in a new tab)

Sources reviewed