LiteLLMModels

Ernie 4.5 300B A47B Paddle API Pricing

As of October 10, 2026, Ernie 4.5 300B A47B Paddle costs $0.28 per 1M input tokens and $1.10 per 1M output tokens on Novita AI. It has a 123,000-token context window and returns up to 12,000 tokens per response.

By BaiduModel ID novita/baidu/ernie-4.5-300b-a47b-paddlePrices updated Checked
Input
$0.28 / 1M tokens
Output
$1.10 / 1M tokens
Context window
123,000 tokens
Max output
12,000 tokens
Providers
1
Added to LiteLLM
January 2026

Ernie 4.5 300B A47B Paddle pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputContext
Novita AInovita/baidu/ernie-4.5-300b-a47b-paddle$0.28$1.10123K

What Ernie 4.5 300B A47B Paddle costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Novita AI$1.11

100 long-document requests with 100,000 input and 2,000 output tokens each

Novita AI$3.02

Ernie 4.5 300B A47B Paddle features

Use Ernie 4.5 300B A47B Paddle with LiteLLM

Call Ernie 4.5 300B A47B Paddle through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="novita/baidu/ernie-4.5-300b-a47b-paddle",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: ernie-4.5-300b-a47b-paddle
    litellm_params:
      model: novita/baidu/ernie-4.5-300b-a47b-paddle
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "ernie-4.5-300b-a47b-paddle",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Ernie 4.5 300B A47B Paddle FAQ

How much does Ernie 4.5 300B A47B Paddle cost?

Ernie 4.5 300B A47B Paddle costs $0.28 per 1M input tokens and $1.10 per 1M output tokens on Novita AI.

What is the context window of Ernie 4.5 300B A47B Paddle?

Ernie 4.5 300B A47B Paddle has a 123,000-token context window and returns up to 12,000 tokens per response.

Which providers offer Ernie 4.5 300B A47B Paddle?

Ernie 4.5 300B A47B Paddle is available from Novita AI through LiteLLM, using the model name novita/baidu/ernie-4.5-300b-a47b-paddle.

How do I call Ernie 4.5 300B A47B Paddle with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/baidu/ernie-4.5-300b-a47b-paddle", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Ernie 4.5 300B A47B Paddle support?

Ernie 4.5 300B A47B Paddle supports structured output.

When did LiteLLM add Ernie 4.5 300B A47B Paddle?

Ernie 4.5 300B A47B Paddle was added to LiteLLM's model price file in January 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request.

Provider pages: Novita AI.