ERNIE 4.5 21B A3B Thinking
Baidu Qianfan ERNIE 4.5 21B A3B Thinking — pricing, 131k context window, API cost calculator and alternatives.
Specs
- Provider
- Baidu Qianfan
- Slug
- baidu/ernie-4-5-21b-a3b-thinking
- Capabilities
- text-only
Pricing freshness
- Tier
- standard
- Currency
- USD
- As of
- 2026-05-08 17:08 UTC
Pricing history
Tracking ERNIE 4.5 21B A3B Thinking pricing since 2026-05-08. We'll plot the chart here once it changes.
Quickstart — call ERNIE 4.5 21B A3B Thinking from your app
curl https://openrouter.ai/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-d '{
"model": "baidu/ernie-4-5-21b-a3b-thinking",
"messages": [{"role": "user", "content": "Hello!"}]
}'Official docs: https://openrouter.ai/docs
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key=os.environ["OPENROUTER_API_KEY"],
)
resp = client.chat.completions.create(
model="baidu/ernie-4-5-21b-a3b-thinking",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Official docs: https://openrouter.ai/docs
// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const resp = await client.chat.completions.create({
model: "baidu/ernie-4-5-21b-a3b-thinking",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);Official docs: https://openrouter.ai/docs
Related models
Similar capabilities, context window, and price tier — drawn from across the catalog so you can compare alternatives in one click.
Frequently asked questions
What is ERNIE 4.5 21B A3B Thinking?
ERNIE 4.5 21B A3B Thinking is a large language model API from Baidu Qianfan with a 131k-token context window. It costs $0.07 per 1M input tokens and $0.28 per 1M output tokens.
How much does ERNIE 4.5 21B A3B Thinking cost?
ERNIE 4.5 21B A3B Thinking is priced at $0.07 per 1M input tokens and $0.28 per 1M output tokens via the Baidu Qianfan API. A 50/50 input/output workload of 1M total tokens costs about $0.175.
What is the context window of ERNIE 4.5 21B A3B Thinking?
ERNIE 4.5 21B A3B Thinking supports up to 131k tokens of context per request — roughly 262 pages of English text or 16384 lines of code at a typical density.
Does ERNIE 4.5 21B A3B Thinking support vision, tool use, or JSON mode?
ERNIE 4.5 21B A3B Thinking is a text-only model — it does not support vision, tool use, or structured JSON mode.
Who makes ERNIE 4.5 21B A3B Thinking?
ERNIE 4.5 21B A3B Thinking is built and operated by Baidu Qianfan. Pricing, context window, and capabilities on this page are refreshed nightly from Baidu Qianfan's public catalog.
Can I self-host ERNIE 4.5 21B A3B Thinking?
ERNIE 4.5 21B A3B Thinking is API-only — its weights are not publicly distributed by Baidu Qianfan, so it cannot be self-hosted today.