ERNIE-4.5-21B-A3B-Thinking
NovitaAIOpen weights
ERNIE-4.5-21B-A3B-Thinking by NovitaAI costs $0.07 per 1M input tokens and $0.28 per 1M output tokens, with a 131K-token context window.
Pricing
Input (per 1M tokens)
$0.07
Output (per 1M tokens)
$0.28
Cached input (per 1M)
—
Specifications
- Provider
- NovitaAI
- Context window
- 131K tokens
- Parameters
- —
- Released
- Sep 2025
- Open weights
- Yes
- Frontier model
- No
Compare ERNIE-4.5-21B-A3B-Thinking with…
ERNIE-4.5-21B-A3B-Thinking vs ERNIE 4.5 300B A47B$1.10/1MERNIE-4.5-21B-A3B-Thinking vs ERNIE-4.5-VL-28B-A3B-Thinking$0.39/1MERNIE-4.5-21B-A3B-Thinking vs L31 70B Euryale V2.2$1.48/1MERNIE-4.5-21B-A3B-Thinking vs Qwen2.5 VL 72B Instruct$0.80/1MERNIE-4.5-21B-A3B-Thinking vs Qwen3 30B A3B$0.45/1MERNIE-4.5-21B-A3B-Thinking vs Qwen 2.5 72B Instruct$0.40/1M
FAQ
How much does ERNIE-4.5-21B-A3B-Thinking cost?
ERNIE-4.5-21B-A3B-Thinking is priced at $0.07 per 1M input tokens and $0.28 per 1M output tokens. Output tokens cost more than input.
What is ERNIE-4.5-21B-A3B-Thinking's context window?
ERNIE-4.5-21B-A3B-Thinking supports a context window of 131K tokens — the maximum prompt plus response length it can handle in a single request.
Is ERNIE-4.5-21B-A3B-Thinking open weight?
Yes — ERNIE-4.5-21B-A3B-Thinking has openly available weights.
Data as of 2026-06-28. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.