ERNIE 5.5 Flash Preview
Baidu logo

ERNIE 5.5 Flash Preview

ernie-5.5-flash-previewllms.txt
Baidu
New
ERNIE 5.5 Flash Preview is the latest foundational model in Baidu's Wenxin (ERNIE) series, comprehensively optimized for programming, agents, knowledge work, and deep research. It has 280 billion total parameters, activates 14 billion parameters per token, and supports a 1M-token context window.

Pricing

TierPricingCache Read
Off-peak · 14:00–00:00 UTC
$0.147$0.588
$0.0147/M tokens
Peak · 00:00–14:00 UTC
$0.2942$1.1768
$0.0294/M tokens

Input Modalities

  • Text

Output Modalities

  • Text

Context length

  • 1M tokens

Max output

  • 1M tokens

Capabilities

  • Thinking
  • Streaming
  • Tool calling
  • Web search
  • URL context
  • Code interpreter
  • Computer use
  • File search
  • Memory tool
  • Structured outputs
  • Structured decision
  • Citations
  • Prompt caching
  • Background mode
  • Server-side sessions

Providers

Baidu ernie-5.5-flash-preview
Off-peak14:00–00:00 UTC
Pricing$0.147$0.588
Cache Read$0.0147/M tokens
Peak00:00–14:00 UTC
Pricing$0.2942$1.1768
Cache Read$0.0294/M tokens
PrecisionⓘNot Disclosed
Latency4.8S
Throughput54.1TPS
Uptime
100.00% uptime 2 days ago
100.00% uptime yesterday
99.41% uptime today

Performance for ernie-5.5-flash-preview

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://aihubmix.com/v1",
)

response = client.chat.completions.create(
    model="ernie-5.5-flash-preview",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

print(response.choices[0].message.content)

Frequently asked questions

What is ERNIE 5.5 Flash Preview?

ERNIE 5.5 Flash Preview is the latest foundational model in Baidu's Wenxin (ERNIE) series, comprehensively optimized for programming, agents, knowledge work, and deep research. It has 280 billion total parameters, activates 14 billion parameters per token, and supports a 1M-token context window.