Baidu: ERNIE 4.5 21B A3B

Public pricingIntelligence 79/100Medium memoryTool use

Baidu: ERNIE 4.5 21B A3B is a text model for vision-language understanding. It combines multimodal input handling with a 120K tokens context window and a low-cost profile. Use it for vision-language understanding and content analysis when quality, speed, and cost matters. It is a practical choice for teams that need reliable output, flexible deployment, and room to scale.

Input

$0.07/1M

Output

$0.28/1M

Cached

$0.01/1M

Batch

$0.04/1M

Calculate your ERNIE 4.5 21B A3B bill.

Set your workload — see cost at your exact volume.

What would ERNIE 4.5 21B A3B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

ERNIE 4.5 21B A3B at a glance.

Memory

120,000

tokens

Max reply

8,000

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

—

Released

Jun 2025

Training cutoff

Feb 2025

Availability

Public pricing

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick ERNIE 4.5 21B A3B

  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

ERNIE 4.5 21B A3B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, ERNIE 4.5 21B A3B costs roughly $16 per month. Input is $0.07 /1M tokens and output is $0.28 /1M tokens.
ERNIE 4.5 21B A3B has a 120,000-token context window (medium memory — a long report or a codebase file). That means you can fit about 22,500 words of input and history in a single call.
Beyond text generation, ERNIE 4.5 21B A3B supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
ERNIE 4.5 21B A3B was released in June 2025, with training data cut off around February 2025.
Models in a similar class include ERNIE 4.5 21B A3B Thinking, ERNIE 4.5 VL 28B A3B, ERNIE 4.5 300B A47B. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare ERNIE 4.5 21B A3B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard