All AI models · LLM benchmarks · Methodology

Baidu

ERNIE 4.5 21B A3B

Open-weight instruction model for adaptable chat and self-hosted production workloads

Model facts

Context window
12K tokens
Maximum output
8K tokens
Cheapest paid input
$0.07 per 1M tokens
Cheapest paid output
$0.28 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.07 input / $0.28 output per 1M tokens

API providers

  • NovitaAI — model id baidu/ernie-4.5-21B-a3b; $0.07 input / $0.28 output per 1M tokens; provider documentation