BytePlus: DeepSeek V3.2
This model is no longer available.Add AI to your application with Puter.js.
Explore Other ModelsModel Card
DeepSeek V3.2 is a mixture-of-experts large language model from DeepSeek, made available here through BytePlus's Model Ark hosting.
It uses DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that lowers compute cost while preserving quality on long-context tasks, and it supports tool use in both thinking and non-thinking modes.
DeepSeek describes its reasoning performance as in the same class as GPT-5, trained with a large-scale agentic data synthesis pipeline spanning over 1,800 environments and more than 85,000 complex instructions to strengthen tool-use in agentic settings.
It's suited for reasoning-heavy work such as math and coding, and for agentic applications that call tools as part of multi-step tasks, while balancing inference speed against the deeper reasoning of DeepSeek's higher-compute Speciale variant.
Context Window 128K
tokens
Max Output 32K
tokens
Input Cost $0.28
per million tokens
Output Cost $0.42
per million tokens
Input text
modalities
Tool Use Yes
Release Date Dec 1, 2025
Code Example
Add AI to your app with the Puter.js AI API, no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From BytePlus
Dola Seedream 5.0 Flash
Dola Seedream 5.0 Flash is ByteDance's fast, lower-cost image generation and editing model in the Seedream 5.0 family, offered here through BytePlus's ModelArk API under the "Dola" branding. It supports text-to-image and reference-guided editing with up to 10 input images, local edits targeted with point and bounding-box coordinates in the prompt, transparent-background output, and decomposition of an image into separate transparent layers. Output is 1K to 2K. BytePlus positions it as "faster image creation, stronger layouts, lower cost at scale." A third-party launch-day test reported 15 to 20 seconds per text-to-image request. It is the cheapest model in the Seedream 5.0 line, and Dola Seedream 5.0 Pro remains the better choice for photorealism and fine material detail. It suits high-volume work such as ad concepts, thumbnails, social visuals, and rapid design iteration.
ChatDeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a Mixture-of-Experts chat model from DeepSeek, made available here through BytePlus's ModelArk platform. It succeeds DeepSeek V4 Flash, keeps a 1 million token context window, and accepts text and image input. In DeepSeek's own tests it scored 90.6 on Terminal-Bench 2.1, ahead of Claude Opus 5 (89.1) and GPT-5.6 Sol (88.8), and 74.2 on DeepSWE v1.1 versus 74.0 for Claude Opus 5. DeepSeek also reports it outperforming the larger V4 Pro. It supports tool calling and up to 384,000 output tokens, which suits coding agents, tool-calling pipelines, and long-context workloads at $0.30 per million input tokens and $1.20 per million output tokens.
ChatGLM-5.3 Flash
GLM-5.3 Flash is a multimodal Mixture-of-Experts model from Zhipu AI (Z.ai), available here through BytePlus's hosted API. It has 320 billion total parameters with 18 billion active per token, accepts text and image input, and supports a 1 million token context window. Z.ai reports 84.3 on Terminal-Bench 2.1 and 63.4 on DeepSWE v1.1 (GLM-5.2 scored 46.2). On Terminal-Bench 2.1 that is close to Claude Opus 4.8 at 85.0. Artificial Analysis gives it 57 on its Intelligence Index, three points behind the larger GLM-5.3. It is the lower-cost model in the GLM-5.3 family and supports tool calling. It suits coding agents and multi-step automation where per-token price matters.
Frequently Asked Questions
DeepSeek V3.2 is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.28 |
| Output | $0.42 |
DeepSeek V3.2 was created by BytePlus and released on Dec 1, 2025.
DeepSeek V3.2 supports a context window of 128K tokens. For reference, that is roughly equivalent to 256 pages of text.
DeepSeek V3.2 can generate up to 32K tokens in a single response.
DeepSeek V3.2 accepts the following input types: text. It produces: text.
Yes, DeepSeek V3.2 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the DeepSeek V3.2 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials