Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

ERNIE-4.5-VL-28B-A3B-Thinking vs ERNIE-4.5-21B-A3B-Thinking

ERNIE-4.5-21B-A3B-Thinking is cheaper on output tokens. Choose ERNIE-4.5-VL-28B-A3B-Thinking or ERNIE-4.5-21B-A3B-Thinking based on the trade-off between cost, context, and the benchmarks that matter for your use case.

SpecERNIE-4.5-VL-28B-A3B-ThinkingERNIE-4.5-21B-A3B-Thinking
ProviderNovitaAINovitaAI
Input / 1M tokens$0.39$0.07
Output / 1M tokens$0.39$0.28
Context window131K131K
Parameters——
Open weightsYesYes
ReleasedNov 2025Sep 2025
ERNIE-4.5-VL-28B-A3B-Thinking details →ERNIE-4.5-21B-A3B-Thinking details →

FAQ

Is ERNIE-4.5-VL-28B-A3B-Thinking or ERNIE-4.5-21B-A3B-Thinking cheaper?

ERNIE-4.5-21B-A3B-Thinking is cheaper on output tokens ($0.28 vs $0.39 per 1M).

Which has the larger context window, ERNIE-4.5-VL-28B-A3B-Thinking or ERNIE-4.5-21B-A3B-Thinking?

Both models offer a similar context window.

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.