Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide

Baidu: Qianfan CoBuddy

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

CoBuddy is a code generation model from Baidu, released through the Qianfan platform and optimized for coding tasks and AI agent workflows.

The model offers native support for both tool calling and reasoning, making it a strong fit for agentic use cases where the model needs to plan, invoke tools, and iterate. It provides a 131K token context window with up to 65K output tokens, giving it ample room for large codebases and extended generation.

CoBuddy is engineered for high inference throughput and low end-to-end latency. It's a solid choice for developers building code-centric agents or assistive coding tools who need responsive performance alongside structured tool use.

Context Window 131K

tokens

Max Output 66K

tokens

Input Cost $0

per million tokens

Output Cost $0

per million tokens

Release Date May 6, 2026

 

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 Baidu

Find other Baidu models →

Chat

ERNIE 5.5 Flash Preview

ERNIE 5.5 Flash Preview is a text model from Baidu and the newest foundation model in the ERNIE family, with 280 billion total parameters. Baidu lists improvements in coding, agentic tasks, knowledge work, and deep research. The model reasons before it answers by default. It supports tool calling and structured output, and it accepts up to 1,024,000 tokens of context with up to 921,600 output tokens. Baidu has not published benchmark scores for this preview. Its published numbers cover only the related ERNIE 5.5 Flash Base checkpoint, released on November 5, 2026. At $0.28 per million input tokens and $1.13 per million output tokens, it fits developers building coding assistants, agents, and long-document research tools who need a very long context window at a low per-token cost.

Chat

ERNIE Light DT 1.0

ERNIE Light DT 1.0 is a text-only large language model from Baidu, offered through Baidu Qianfan's international API. Baidu says it is built on open-source GLM models and draws on research from Baidu Search's Lightning model. Its main feature is Baidu Sparse Attention (BSA) with feedback-driven history compression. Baidu says this lowers KV cache storage and compute costs while maintaining model performance. The model accepts up to 1,024,000 input tokens and can return up to 131,072 output tokens. The API supports tool calling, structured JSON output, and adjustable reasoning effort (max, high, low, or none). Baidu has not published benchmark scores. It fits developers building agents, long-document analysis, or multi-turn workflows that need a very large context window. At $1.13 per million input tokens and $3.94 per million output tokens, it costs more than Baidu's ERNIE 5.5 Flash Preview, so it makes most sense for long-context work.

Frequently Asked Questions

How do I use Qianfan CoBuddy?

Qianfan CoBuddy is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for Qianfan CoBuddy?
Qianfan CoBuddy costs $0 per 1M input tokens and $0 per 1M output tokens.
Price per 1M tokens
Input$0
Output$0
Who created Qianfan CoBuddy?

Qianfan CoBuddy was created by Baidu and released on May 6, 2026.

What is the context window of Qianfan CoBuddy?

Qianfan CoBuddy supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of Qianfan CoBuddy?

Qianfan CoBuddy can generate up to 66K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Qianfan CoBuddy 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