LiteLLMModels

Ernie 4.5 21B A3B Thinking API Pricing

As of October 10, 2026, Ernie 4.5 21B A3B Thinking costs $0.07 per 1M input tokens and $0.28 per 1M output tokens on Novita AI. It has a 131,072-token context window and returns up to 65,536 tokens per response.

By BaiduModel ID novita/baidu/ernie-4.5-21B-a3b-thinkingPrices updated Checked
Input
$0.07 / 1M tokens
Output
$0.28 / 1M tokens
Context window
131,072 tokens
Max output
65,536 tokens
Providers
1
Added to LiteLLM
January 2026

Ernie 4.5 21B A3B Thinking 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-4.5-21B-a3b-thinking$0.07$0.28128K

What Ernie 4.5 21B A3B Thinking costs in practice

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

Novita AI$0.28

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

Novita AI$0.756

Ernie 4.5 21B A3B Thinking features

Use Ernie 4.5 21B A3B Thinking with LiteLLM

Call Ernie 4.5 21B A3B Thinking 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-4.5-21B-a3b-thinking",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: ernie-4.5-21b-a3b-thinking
    litellm_params:
      model: novita/baidu/ernie-4.5-21B-a3b-thinking
      # 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-4.5-21b-a3b-thinking",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Ernie 4.5 21B A3B Thinking FAQ

How much does Ernie 4.5 21B A3B Thinking cost?

Ernie 4.5 21B A3B Thinking costs $0.07 per 1M input tokens and $0.28 per 1M output tokens on Novita AI.

What is the context window of Ernie 4.5 21B A3B Thinking?

Ernie 4.5 21B A3B Thinking has a 131,072-token context window and returns up to 65,536 tokens per response.

Which providers offer Ernie 4.5 21B A3B Thinking?

Ernie 4.5 21B A3B Thinking is available from Novita AI through LiteLLM, using the model name novita/baidu/ernie-4.5-21B-a3b-thinking.

How do I call Ernie 4.5 21B A3B Thinking with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/baidu/ernie-4.5-21B-a3b-thinking", 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 21B A3B Thinking support?

Ernie 4.5 21B A3B Thinking supports reasoning.

When did LiteLLM add Ernie 4.5 21B A3B Thinking?

Ernie 4.5 21B A3B Thinking 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.