ERNIE 5.0 overview
ERNIE 5.0 by Baidu
With advanced reasoning, multimodal understanding, and global language support, ERNIE 5.0 is redefining how AI interacts with complex data.
ERNIE 5.0 specs
- Model ID
baidu/ernie-5.0- Developer
- Baidu
- Context window
- 128,000 tokens
- Max output
- 65,536 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
ERNIE 5.0 is a large-scale foundation model with trillions of parameters designed for high‑accuracy language and multimodal understanding. It is developed by Baidu and positions itself among the strongest global models in reasoning, instruction following, and creative tasks.
- ERNIE 5.0 supports text, image, audio, and video inputs and outputs as a native capability, not as an add‑on.
- Benchmarks show performance comparable to leading international systems across language and multimodal tasks.
- Designed for high-performance, complex reasoning tasks
- Provides maximum accuracy and advanced multimodal functionality for enterprise-grade applications
Enhanced Multimodal Capabilities
Seamlessly process and integrate text, images, video, and audio for unified AI understanding.
Use cases
ERNIE 5.0 is documented as suited to multimodal understanding and generation across text, images, audio, and video. It is also described as useful for instruction following and agentic tool-use tasks. The model is further documented for creative writing. It is also cited for factual reasoning and document understanding, including image-based QA and chart/document analysis.
Capabilities
- Function calling
- Streaming
- Structured outputs
ERNIE 5.0 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $1.4 | 1M tokens |
| Output | $5.6 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
ERNIE 5.0 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| $1.4 | $5.6 | |
| $0.429 | $1.29 | |
| $3.17 | $5.29 | |
| $2 | $6 | |
| $2 | $6 |
How to use the ERNIE 5.0 API
View docsBuild with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "baidu/ernie-5.0",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "baidu/ernie-5.0",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "baidu/ernie-5.0",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Related articles
ERNIE 5.0 FAQ
What is the context window of ERNIE 5.0?
ERNIE 5.0 has a 128,000 tokens context window and can return up to 65,536 tokens.
What inputs and outputs does ERNIE 5.0 support?
ERNIE 5.0 takes image, text as input and returns text.
What is the model ID for ERNIE 5.0?
Use baidu/ernie-5.0 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
How much does ERNIE 5.0 cost?
ERNIE 5.0 costs $1.4 input and $5.6 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does ERNIE 5.0 support streaming?
Yes, ERNIE 5.0 can stream responses as they are generated.
Can ERNIE 5.0 read images?
Yes, ERNIE 5.0 accepts image input alongside text.
Who created ERNIE 5.0?
ERNIE 5.0 was built by Baidu.

