Get an email when this model's blended price drops. No account needed.
One email per drop. Unsubscribe anytime.
Daily blended price ($/1M) — recorded each day, builds into a trend over time.
Typical 3:1 output-to-input mix, per 1M tokens
Price as of 2026-05-10 · Source: baidu_qianfan_official_pricing
Complex reasoning, analysis, planning and multi-step problem solving where answer quality matters more than raw cost.
ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level...
ernie-4.5-21b-a3b-thinking is a Reasoning model from Baidu Wenxin (CN). HotON.ai tracks it at $0.07 per 1M input tokens and $0.28 per 1M output tokens, with a 131K-token context window. Its composite efficiency score is 89/100 at an estimated $0.000 per successful task.
ernie-4.5-21b-a3b-thinking is tracked at $0.07 per 1M input tokens and $0.28 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.23 per 1M tokens. Figures are illustrative demo data.
Complex reasoning, analysis, planning and multi-step problem solving where answer quality matters more than raw cost.
ernie-4.5-21b-a3b-thinking supports up to a 131K-token context window — large enough for long documents and extended conversations in a single request.
Within the HotON.ai tracked set, ernie-4.5-21b-a3b-thinking is cheaper than 88% of models on input price and ranks #205 of 535 by overall efficiency.
Ready to paste into articles, papers or AI prompts — prices and date refresh with the live data.
HotON.ai — ernie-4.5-21b-a3b-thinking (Baidu Wenxin): $0.07/1M input, $0.28/1M output, as of 2026-05-10. https://hoton.ai/en/models/baidu-ernie-4-5-21b-a3b-thinkingPricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Efficiency is a modeled composite of real price and context.