LLM Reference

ERNIE 4.5 21B A3B

Released
2026-01-01
Last refreshed
2026-06-04
Status
Researched 7d ago
Open SourceCommercial use allowedAgentsClassificationJSON / Tool use

ERNIE 4.5 21B A3B is worth evaluating for agents, classification, and json / tool use when its provider route and context window match the workload.

Use it for

  • Teams evaluating agents, classification, and json / tool use
  • Workloads that can use a 120k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Vision or document-understanding workloads
Specifications
Family
ERNIE 4.5
Released
2026-01-01
Context
120k
Parameters
21B
Architecture
moe
Specialization
general
Openness
Open source
License
Apache 2.0(OSI)Commercial use allowed
Training
pretrained
Created by

Innovative text-to-video and app builder

Beijing, China
Founded 2010
Website
Pricing
Output / 1M
$0.280
Input / 1M
$0.070

Cheapest of 1 route · Novita AI

About

ERNIE 4.5 21B A3B is a Mixture-of-Experts model from Baidu with 21B total parameters and 3B activated per token. It delivers strong performance across Chinese and English language tasks with efficient inference at 120K context.

ERNIE 4.5 21B A3B is an open-source model in the ERNIE 4.5 family. The structured metadata tracks a 120k-token context window, function calling, tool use, and structured outputs. This page tracks provider routes through Novita AI, with the cheapest tracked route listed at $0.07 input and $0.28 output per 1M tokens. No headline benchmark score is tracked for ERNIE 4.5 21B A3B yet.

Top use-case fit: coding, agents, and build tasks

Agents

Included by capability and metadata signals in the decision map.

Classification

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.070$0.280
Serverless

Capabilities

Function CallingTool UseStructured Outputs

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.