Hy3 vs MiMo V2.5

Hy3 from Tencent Hunyuan and MiMo V2.5 from Xiaomi MiMo are shown side by side so you can compare pricing, model IDs, context and output limits, modalities, tool use, release details, and benchmark results where data is available.

Overall Recommendation

This Tencent Hunyuan 3 (Hy3) vs Xiaomi MiMo V2.5 comparison comes down to modality and context. Choose Xiaomi MiMo V2.5 for multimodal input or workloads that need up to a 1M-token context window. Choose Tencent Hy3 for text-first coding, office, and tool-using agents when its smaller 295B/21B-active MoE and the three TokenHub-compatible endpoints are the better operational fit. TokenHub does not currently publish enough MiMo pricing data here for a cost winner.

Comparison Highlights

Based On Current Page Data

Hy3Tencent Hunyuan

MiMo V2.5Xiaomi MiMo

How To Read It

Best For

Text-first codingoffice worktool-using agents

Multimodal understandingmillion-token agent workflows

How To Read ItUse-case synthesis from model capabilities and positioning.

Workload Fit

256K contextReasoning modesAgent workflows

1M contextTextimagevideoaudioAgentic tasks

How To Read ItThe workloads each model is most directly shaped for.

Input

$0.1429/M

$0.14/MEdge

How To Read ItLower is better when prompts or retrieval payloads are large.

Output

$0.5714/M

$0.28/MEdge

How To Read ItLower is better for reasoning-heavy or long-generation traffic.

Context length

256K

1.1MEdge

How To Read ItHigher is better for repositories, retrieval packs, and transcripts.

Input modalities

Text

Audio, Image, Text, VideoEdge

How To Read ItBroader input support reduces the need for separate vision or video models.

Model Selection Guide

Hy3Tencent Hunyuan

Choose Hy3 When

Tencent describes Hy3 as a 295B-parameter MoE with 21B active parameters and a 256K context window
The official release focuses on reasoning, coding, office productivity, long-context work, and reliable tool calls
TokenHub currently lists OpenAI Chat, OpenAI Responses, and Claude Messages endpoints for model ID hy3

MiMo V2.5Xiaomi MiMo

Choose MiMo V2.5 When

Xiaomi describes MiMo V2.5 as a 310B-parameter sparse MoE with 15B active parameters and up to 1M context
Its native architecture accepts text, image, video, and audio rather than text alone
Official deployment examples expose OpenAI-compatible chat completions with reasoning and MiMo tool-call parsers

Basic Information

Hy3Tencent Hunyuan

MiMo V2.5Xiaomi MiMo

Name

Hy3

Model id

hy3

Data source

TokenHub production catalog

Intro

Tencent Hunyuan 3 (Hy3) is a Tencent Hunyuan large language model for reasoning, coding, long-context analysis, and agent workflows. Often searched as Tencent Hy3, Hunyuan 3, or simply Hunyuan, it is part of the Tencent Hunyuan model family alongside releases such as Hunyuan A13B. On TokenHub, developers can review the current Tencent Hunyuan 3 model ID, API pricing, context window, and supported endpoints before integrating it into production applications.

Author

Tencent Hunyuan

Released date

2026-07-06

Context length

256K

Max output tokens

128K

Name

MiMo V2.5

Model id

mimo-v2.5

Data source

TokenHub production catalog

Intro

Xiaomi MiMo V2.5 is Xiaomi’s native multimodal Mixture-of-Experts model for production AI applications. It can understand text, images, video, and audio, while generating high-quality text for chat, coding, reasoning, content generation, and agent workflows. With a long-context design and tool-use capabilities, MiMo V2.5 is suited to document analysis, multimodal assistants, structured extraction, and complex tasks that need to combine multiple input formats.

Author

Xiaomi MiMo

Released date

2026-04-23

Context length

1.1M

Max output tokens

131.1K

Name

Hy3

Name

MiMo V2.5

Model id

hy3

Model id

mimo-v2.5

Data source

TokenHub production catalog

Data source

TokenHub production catalog

Intro

Author

Tencent Hunyuan

Author

Xiaomi MiMo

Released date

2026-07-06

Released date

2026-04-23

Context length

256K

Context length

1.1M

Max output tokens

128K

Max output tokens

131.1K

Pricing

Hy3Tencent Hunyuan

MiMo V2.5Xiaomi MiMo

Input

$0.1429/M

Output

$0.5714/M

Cached input

$0.0357/M

Input

$0.14/M

Output

$0.28/M

Cached input

$0.0028/M

Input

$0.1429/M

Input

$0.14/M

Output

$0.5714/M

Output

$0.28/M

Cached input

$0.0357/M

Cached input

$0.0028/M

Capabilities

Hy3Tencent Hunyuan

MiMo V2.5Xiaomi MiMo

Reasoning

Knowledge

n/a

Attachment

Input modalities

Text

Output modalities

Text

Temperature

Tool use

Reasoning

Knowledge

n/a

Attachment

Input modalities

Audio, Image, Text, Video

Output modalities

Text

Temperature

Tool use

Reasoning

Knowledge

n/a

Knowledge

n/a

Attachment

Input modalities

Text

Input modalities

Audio, Image, Text, Video

Output modalities

Text

Output modalities

Text

Temperature

Tool use

Benchmark

Hy3Tencent Hunyuan

MiMo V2.5Xiaomi MiMo

Intelligence

wins42.2

Coding

wins58.8

Intelligence

Coding

56.8

FAQ

Which model is better, Hy3 or MiMo V2.5?

Neither model is universally better. Start with the Model Selection Guide above to match each model to your task, then use pricing, context length, maximum output, and capability rows to confirm the operational fit.

Is MiMo V2.5 cheaper than Hy3?

Use the pricing rows above to compare input, output, and cached input prices for Hy3 and MiMo V2.5.

Which model supports a longer context length?

Hy3 lists 256K context length, while MiMo V2.5 lists 1.1M.

Can I access both models through TokenHub?

If both models are available in the TokenHub catalog, you can route requests to Hy3 and MiMo V2.5 through the TokenHub API.