AI 模型情報

廠商 · 2026-08-14

baidu

8 個標準模型8 條紀錄(含衍生 / 微調)
模型輸入 / 1M輸出 / 1M上下文服務商標籤
ERNIE-4.5-21B-A3B-Thinking$0.070$0.280131K1reasoning · open-weights
ERNIE 4.5 21B A3B$0.070$0.280120K1tools · open-weights
ERNIE 4.5 VL 28B A3B$0.140$0.56030K1tools · reasoning · vision · open-weights
ERNIE-4.5-VL-28B-A3B-Thinking$0.390$0.390131K1tools · json · reasoning · vision · open-weights
ERNIE 4.5 300B A47B$0.280$1.10123K2tools · json · open-weights
baidu/ERNIE-4.5-300B-A47B$0.280$1.10131K2tools · json
ERNIE 4.5 VL 424B A47B $0.420$1.25123K4reasoning · vision · open-weights
ERNIE 5.0$0.840$3.37128K1tools · reasoning · vision

Frequently asked questions

How many AI models does baidu offer?

We track 8 canonical baidu models. The list is recomputed daily.

Which baidu model is the cheapest?

ERNIE-4.5-21B-A3B-Thinking is currently the lowest-priced baidu model, at $0.070 per 1M input tokens and $0.280 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Which baidu model has the largest context window?

ERNIE-4.5-21B-A3B-Thinking leads at 131K tokens. This is the total of prompt + completion.

Which baidu models support tool calling?

Multiple baidu models support tool calling, with ERNIE 4.5 21B A3B being a popular pick. The capability column in the table above marks every model with baidu tool-calling support.

Which baidu models accept image input?

ERNIE 4.5 VL 28B A3B accepts image input. Other vision-capable baidu models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to baidu?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this baidu pricing data?

Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

最近更新:

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.