Интерфейс моделей ИИ

baidu/ERNIE-4.5-300B-A47B

baidu/ernie-4-5-300b-a47b

От baidu · семейство: ernie · выпуск 2025-07-02

$0.280
Вход / 1M токенов
$1.10
Выход / 1M токенов
131K
Окно контекста
131K
Макс. вывод

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

Возможности

Tool callingРассуждениеСтруктурированный выводВложенияОткрытые весаУправление температурой
Модальности: вход text · выход text

Model fit scores

0–100 · higher is better

These scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.

Coding65
  • Tool calling40/40
  • Structured output20/20
  • Reasoning0/10
  • Context window (100K → 1M)2/20
  • Provider availability3/10
Agents78
  • Tool calling35/35
  • Structured output25/25
  • Reasoning0/15
  • Output token limit15/15
  • Provider availability3/10
JSON / structured output97
  • Structured output / JSON mode50/50
  • Tool calling20/20
  • Temperature control10/10
  • Price-friendly for high-volume17/20
Cost efficiency59
  • Headline price (log-scaled)59/95
  • Has prompt-cache pricing0/5
Long context46
  • Context window (100K → 2M)36/90
  • Has published price for full window10/10
Production-readiness73
  • Number of independent providers15/40
  • Has published per-token price20/20
  • Context window ≥ 8K15/15
  • No data inconsistencies across providers8/10
  • Official model (not derivative)15/15

Cost Efficiency Index

Open full calculator →

Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.

ScenarioCostAssumption
RAG answer
per 1,000 RAG answers
$1.95
< $0.01 per request
5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot.
Support ticket triage
per 10,000 tickets
$3.90
< $0.01 per request
1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support.
Data extraction
per 1,000 documents
$1.11
< $0.01 per request
2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines.
Code review
per 1,000 PRs
$3.34
< $0.01 per request
8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads.
Agent step
per 1,000 steps
$4.02
< $0.01 per request
12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step.

Детализация цен

Рекомендованная цена от siliconflow-cn · baidu/ERNIE-4.5-300B-A47B

$0.280
Вход
$1.10
Выход

Доступна у 3 провайдеров

ПровайдерID модели провайдераВход / 1MВыход / 1MКонтекстВыпуск
SiliconFlow (China)
siliconflow-cn
baidu/ERNIE-4.5-300B-A47B$0.280$1.10131K2025-07-02
SiliconFlow
siliconflow
baidu/ERNIE-4.5-300B-A47B$0.280$1.10131K2025-07-02
Kilo Gateway
kilo
baidu/ernie-4.5-300b-a47b$0.280$1.10123K2025-06-30

Расхождения данных между провайдерами

  • context_window varies: 123000, 131000

Провайдеры сообщают разные значения для этой модели. Сводка выше использует репрезентативного провайдера; детали — в таблице.

Frequently asked questions

How much does baidu/ERNIE-4.5-300B-A47B cost?

baidu/ERNIE-4.5-300B-A47B costs $0.280 per 1M input tokens and $1.10 per 1M output tokens, sourced from siliconflow-cn. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.

What is the context window of baidu/ERNIE-4.5-300B-A47B?

baidu/ERNIE-4.5-300B-A47B has a context window of 131K tokens, with a max output of 131K tokens per reply. This is the total combined size of prompt + completion.

Does baidu/ERNIE-4.5-300B-A47B support tool calling?

Yes. baidu/ERNIE-4.5-300B-A47B supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Does baidu/ERNIE-4.5-300B-A47B support structured output / JSON mode?

Yes. baidu/ERNIE-4.5-300B-A47B supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Can baidu/ERNIE-4.5-300B-A47B accept image input?

No. baidu/ERNIE-4.5-300B-A47B only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.

Is baidu/ERNIE-4.5-300B-A47B open-weight?

No. baidu/ERNIE-4.5-300B-A47B is a proprietary model — only baidu (and any approved hosting partners) can serve it. The pricing above reflects the cheapest API access.

What are the best alternatives to baidu/ERNIE-4.5-300B-A47B?

If baidu/ERNIE-4.5-300B-A47B doesn't fit, consider ERNIE 4.5 VL 424B A47B , ERNIE 4.5 VL 28B A3B, ERNIE 4.5 21B A3B. Each one targets the same use case — see the Related links below for direct head-to-head pages.

Where does this data come from?

All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.

More baidu models

Последнее обновление:

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