LLM ReferenceLLM Reference

Using ERNIE X1.1 on Baidu Qianfan

Implementation guide · ERNIE · Baidu AI

Serverless

Quick Start

  1. 1
    Create an account at Baidu Qianfan and generate an API key.
  2. 2
    Use the Baidu Qianfan SDK or REST API to call ernie-x1.1 — see the documentation for request format.
  3. 3
    You'll be billed $0.15/1M input, $0.59/1M output tokens. See full pricing.

Code Examples

See Baidu Qianfan documentation for integration details.

About Baidu Qianfan

Baidu Qianfan provides native hosted access to Baidu's ERNIE model lineup, including ERNIE 5.1, through model service APIs and the Qianfan console. The platform documents OpenAI-compatible access patterns, model lists, rate limits, and token-based pricing for online inference.

Baidu Qianfan is Baidu Intelligent Cloud's foundation model and Agent development platform, providing hosted API access to ERNIE and Qianfan models for text generation, reasoning, multimodal understanding, embeddings, and agent workflows.

Pricing on Baidu Qianfan

TypePrice (per 1M)
Input tokens$0.15
Output tokens$0.59

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About ERNIE X1.1

ERNIE X1.1 is Baidu's second-generation deep-thinking reasoning model, unveiled at Wave Summit on September 9, 2025. Built on ERNIE 4.5 multimodal foundations with iterative hybrid reinforcement learning and self-distillation. Delivers significant gains over ERNIE X1: factual accuracy up 34.8%, instruction following up 12.5%, agentic capabilities up 9.6%. Surpasses DeepSeek R1-0528 and performs on par with GPT-5 and Gemini 2.5 Pro on key benchmarks. Qianfan lists both ernie-x1.1 and ernie-x1.1-preview endpoints with 64K context and up to 65,536 output tokens.

Model Specs

Released2025-09-09
Context64K

Provider

Baidu Qianfan

Baidu

Beijing, China