SandBase is live — $1 in free credits on signupStart free ›
Start building
Use in agentBaidu models

Baidu modelsChat Completions model

baidu/ernie-4.5-300b-a47b

ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in both English and C...

Input⌘ / Ctrl + Enter

Try a prompt

12K max output
Input $0.28/M · Output $1.10/M
OutputReady

Your response will appear here

Choose an example or write a prompt, then click Run.

API details and access

Model Details

ProviderBaidu
TypeLlm
Model IDbaidu/ernie-4.5-300b-a47b

Capabilities

InputText
OutputText
Context-
Max Output12,000
VisionNot supported
Function CallingNot supported

Access details

Chat Completions
Base URLhttps://api.sandbase.ai
API Endpoint/v1/chat/completions
{
  "model": "baidu/ernie-4.5-300b-a47b",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 512
}

Pricing

Input$0.28 / 1M tokens
Output$1.10 / 1M tokens

Related Models

baidu/ernie-4.5-21b-a3bA sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an extensive 131K token context length, the model achieves efficient inference via multi-expert parallel collaboration and quantization, while advanced post-training techniques including SFT, DPO, and UPO ensure optimized performance across diverse applications with specialized routing and balancing losses for superior task handling.baidu/ernie-4.5-21b-a3b-thinkingERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks.baidu/ernie-4.5-vl-28b-a3bA powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing. Built with scaling-efficient infrastructure for high-throughput training and inference, the model leverages advanced post-training techniques including SFT, DPO, and UPO for optimized performance, while supporting an impressive 131K context length and RLVR alignment for superior cross-modal reasoning and generation capabilities.baidu/ernie-4.5-vl-424b-a47bERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data using a heterogeneous MoE architecture and modality-isolated routing to enable high-fidelity cross-modal reasoning, image understanding, and long-context generation (up to 131k tokens). Fine-tuned with techniques like SFT, DPO, UPO, and RLVR, this model supports both “thinking” and non-thinking inference modes. Designed for vision-language tasks in English and Chinese, it is optimized for efficient scaling and can operate under 4-bit/8-bit quantization.baidu/qianfan-ocr-fastQianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.