LLM Reference

ERNIE 4.5 on Baidu Qianfan

ERNIE · Baidu AI

Serverless

Last refreshed 2026-06-04. Next refresh: weekly.

Why use ERNIE 4.5 on Baidu Qianfan?

Baidu Qianfan offers ERNIE 4.5 with pay-as-you-go pricing at $0.59/1M input tokens. 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.

Compare ERNIE 4.5 across 2 providers to find the best fit for your use case
Input / 1M
$0.59
Output / 1M
$2.36
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: ernie-4.5-8k
Model ID
ernie-4.5-8k

Request example

Curated snippets for this provider are not sourced yet. Use Baidu Qianfan documentation with model ID ernie-4.5-8k.

Gotchas

  • Use provider model ID "ernie-4.5-8k", not the LLMReference slug "ernie-4.5".

Compare ERNIE 4.5 Across Providers

ProviderInput (per 1M)Output (per 1M)
Fireworks AI$1.20$1.20
Baidu Qianfan$0.59$2.36

Pricing

TypePrice (per 1M)
Input tokens$0.59
Output tokens$2.36

Capabilities

VisionMultimodal

About ERNIE 4.5

ERNIE 4.5 is Baidu AI's ERNIE model. It offers an 8K-token context window.

FAQ

What does ERNIE 4.5 cost on Baidu Qianfan?

On Baidu Qianfan, ERNIE 4.5 costs $0.59 per 1M input tokens and $2.36 per 1M output tokens.

What is the context window for ERNIE 4.5 on Baidu Qianfan?

ERNIE 4.5 supports a 8k token context window on Baidu Qianfan.

How does Baidu Qianfan compare to other ERNIE 4.5 providers?

ERNIE 4.5 is available from 2 providers. The cheapest input pricing is $0.59/1M tokens from Baidu Qianfan.

What API model ID do I use for ERNIE 4.5 on Baidu Qianfan?

Use the model ID ernie-4.5-8k when calling Baidu Qianfan's API.

Who created ERNIE 4.5?

ERNIE 4.5 was created by Baidu AI as part of the ERNIE model family.

Is ERNIE 4.5 open source?

ERNIE 4.5 is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2025-03-16
Context8k
ArchitectureDecoder Only