Seedance 2.5 Flash now 35% off — ends Nov 30

Tencent Models on Atlas Cloud | Hunyuan 3D & Hy3 API

Use the Tencent API on Atlas Cloud to run Hunyuan 3 for reasoning and Hunyuan 3D for mesh generation. One key, one bill, pay as you go for both models today.

Tencent is developed by Tencent. Atlas Cloud (operated by Atlas Cloud AI LLC) provides access to it and does not own it. All trademarks belong to their respective owners.

AI Video Models by Tencent

Generate cinematic, high-fidelity videos from text and images with the latest AI video generation models on Atlas Cloud.

View all models

AI Image Models by Tencent

Create stunning, production-ready visuals from prompts and references using state-of-the-art AI image generation models on Atlas Cloud.

View all models

Large Language Models by Tencent

Power chat, reasoning, and agents at scale with leading large language models, served fast and affordably on Atlas Cloud.

View all models

Tencent Models API Pricing Details

Compare standard vs. our pricing across every Tencent model.

ModelStandard Price (USD)Our Price (USD)Discount
Hy4
$0.834/$2.501per 1M tokens1048.6K context
$0.417/$1.25M in/outper 1M tokens1048.6K context
-50%View
Hunyuan 3D Rapid Image-to-3D$0.02/pic
Start from$0.02/pic
—View
Hunyuan 3D Rapid Text-to-3D$0.02/pic
Start from$0.02/pic
—View
Hunyuan 3D Pro Image-to-3D$0.02/pic
Start from$0.02/pic
—View
Hunyuan 3D Pro Text-to-3D$0.02/pic
Start from$0.02/pic
—View
Tencent WAND Vega Video 1.5-pro Reference To Video$0.093
Start from$0.093/s video
—View

Explore models from other providers

Instantly explore and experiment with production-ready models in the Atlas Playground. Start customizing with one click.

Tencent API Use Cases You Can Build on Atlas Cloud

Teams use the Tencent API on Atlas Cloud to run agentic coding, document review, and 3D asset generation from a single account. Hy3 handles reasoning-heavy tasks while Hunyuan 3D turns text and images into production-ready meshes.

Repo-Scale Coding Agents

Hy3 accepts a full codebase inside its 256K context window, enough to reason across many files at once. Developers set reasoning_effort to high so it can trace a bug through the repo and propose a fix. On Atlas Cloud this runs through the same Tencent API endpoint used for chat, with no separate agent infrastructure to stand up.

Contract & Document Review

Hy3 was trained to reduce fabricated clauses and misquotes, which matters when the input is a long contract or regulatory filing. The 256K context window lets it read the full document instead of chunking it into fragments. Legal and compliance teams use this to flag risky clauses before a human reviews the file.

Game Asset Prototyping

Studios feed in a character sketch or reference image and get back a mesh with up to 1.5M faces and 4K PBR textures. Artists then refine the output instead of modeling from a blank scene. Unity China and other studios already use Hunyuan 3D this way to cut early production time.

3D Product Pages for E-commerce

Retailers convert standard product photos into interactive 3D views customers can rotate and zoom. In a furniture trial, Tencent reported a 35 percent lift in click-through rate for listings with a 3D model attached. The GLB and USDZ exports plug directly into most storefront and AR viewers.

Rapid Concept-to-Print Iteration

Makers and 3D printing teams use the Rapid tier to turn a sketch or photo into a printable mesh in 2 to 3 minutes. Each job includes an MP4 preview so you can check the shape before committing to a full-resolution export. Bambu Lab is among the companies building this kind of workflow on top of Hunyuan 3D.

Multi-Tool Agent Orchestration

Hy3 was tuned for tool calling and task planning, not just chat responses, with fixed reliability issues around output formatting. It already drives Tencent's own OS-level assistant for tasks like file editing, file management, and diagnostics. Developers can plug the same Tencent API into their own agent scaffolding on Atlas Cloud.

Render your enterprise vision into reality with Atlas Cloud AI.

Contact Sales

Tencent Hunyuan API FAQ

Hy3 API is Tencent's flagship reasoning model, built for complex problem solving and agentic workflows. It runs on a 295 billion parameter mixture-of-experts architecture with 21 billion active parameters and a 256K context window. On Atlas Cloud you call it through an OpenAI-compatible Tencent API endpoint alongside 400+ other models.

Yes. Hy3 was tuned specifically for agents, not just question answering, and it already powers Tencent's own CodeBuddy assistant in production. Developers can set reasoning_effort to high for multi-step coding tasks or no_think for fast direct answers.

Yes. Tencent open-sourced the final Hy3 release under the Apache 2.0 license after collecting feedback from more than 50 product teams during its preview. Atlas Cloud hosts the Hy3 API so you can call it directly instead of running the weights yourself.

Hunyuan 3D generations start at $0.02 each, billed pay-as-you-go with no subscription required. Hy3 API usage is billed the same way, per token, through the same Atlas Cloud account. One API key covers both models and every other model on the platform.

Explore More Families

Seedance 2.5

The Seedance 2.5 API gives developers ByteDance Seed’s joint audio and video model, generating 4 to 30 seconds in one pass at up to native 4K from text, a first frame, or up to 50 references across images, video, and audio. It edits selected regions, extends clips, and follows white-model and green-screen inputs.

View Family

Seedance 2.5 Flash

The Seedance 2.5 Flash API gives developers the faster, lower-cost tier of ByteDance Seed’s Seedance 2.5, released on November 12, 2026. It generates video at nearly twice the speed of Seedance 2.5, renders up to 30 seconds per clip at 480p or 720p, and takes up to 10 images, 5 videos, and 5 audio clips per request, with video editing for quick variants.

View Family

Kling 4.0

The Kling 4 API delivers Kling 4.0, the video model Kuaishou released on October 15, 2026. It generates up to 30 seconds in a single pass, follows up to 10 keyframes, blends 15 images, videos, and subjects through Omni Reference, and adds stereo audio with lip sync. Atlas Cloud serves all four endpoints, including video editing, on one OpenAI-compatible key from $0.11 per second. Start building today.

View Family

Seedream 5.5

Seedream 5.5 is ByteDance Seed's image generation and editing family. Guide edits with up to 10 reference images, or split an image into a base image and up to 99 editable layers, with optional OCR for text layers. On Atlas Cloud, generation, editing, and layer decomposition each cost a standard $0.02 per image, helping developers plan image workflow budgets. Start building today.

View Family

Kling 4.0 Flash

As a lower-cost option in the Kling 4.0 family, Kling 4.0 Flash combines images, videos, and subjects to create consistent 720p clips lasting 3 to 20 seconds. Start from a text prompt or animate a first-frame image to suit different production workflows. Atlas Cloud offers all four model variants at a standard price of $0.094 per second. Start building today.

View Family

Wan 3.0

Wan 3.0 is Alibaba’s newest video model, producing up to 30 seconds of 1080p video at 30fps with audio in one generation. Steer it with a text prompt, a first frame, up to 10 reference images, or a document. Standard costs less per second, while Prime keeps the same capabilities and returns results faster. Both run on the same Atlas Cloud key as Wan 2.7, 2.6, and 2.5.

View Family

GPT Image 2.6

The GPT Image 2.6 API gives developers OpenAI’s image model released on November 4, 2026, in two versions: Flare for fast iteration and Sunburst for detailed visual work. It generates images 50% faster than before and adds animated GIF output, SVG export, markup edits that target the area you circle, and a complexity setting. Atlas Cloud serves both models on one OpenAI-compatible key with pay-as-you-go pricing.

View Family

Kling Image 4.0

Kling Image 4.0 is Kling AI's image generation model for detailed visual design. Reference images guide compositions, while long layouts bring product imagery and brand messaging into complete page visuals. High resolution output provides room for cropping and display. Atlas Cloud simplifies integration with a unified API and transparent pay-as-you-go pricing. Start building today.

View Family

MiniMax H3 Image

MiniMax H3-Image builds on MiniMax's H3 family, combining image generation and editing in one checkpoint. Detailed prompts guide characters, scenes, and composition, while reference inputs steer visual changes. Atlas Cloud offers hosted access with pay-as-you-go billing, helping you integrate image workflows without managing model infrastructure. Start building today.

View Family

MiniMax H3

MiniMax H3 is MiniMax's multimodal video family for text, image, and reference guided creation. Across supported routes, it preserves subjects from reference media, offers flexible aspect ratios, and pairs generated sound with visuals through H3 Developer, with output profiles selected by endpoint. Atlas Cloud unifies the family behind one OpenAI-compatible key with transparent pay-as-you-go pricing from the standard rate of $0.038 per second. Start building today.

View Family

GPT Image 2.5

GPT Image 2.5 is OpenAI’s image generation and editing model, released on September 8, 2026 in two API versions. Flare is the default, with up to 50% lower latency than GPT Image 2, while Sunburst takes longer to give finer control over detailed edits. Both support up to 16 reference images, five quality tiers, transparent backgrounds, and custom sizes up to 3840px. Atlas Cloud serves the GPT Image 2.5 API at OpenAI’s per token rates, or at a flat price per image by 1K, 2K, or 4K tier.

View Family

Seedream 5.0 Pro

Seedream 5.0 Pro API gives developers ByteDance's controllable image editing model on Atlas Cloud. It places edits precisely with anchors and coordinates, separates images into editable layers, fuses multiple references, and matches exact colors and materials, with multilingual text at 2K and 3K. On Atlas Cloud you reach it through one key!

View Family

Recommended Articles

Guides, tutorials, and product updates to help you get the most out of Atlas Cloud.