baidu · Balanced
ERNIE 5.1 Thinking
ERNIE 5.1 Thinking is the latest Wenxin model with explicit reasoning enabled for harder planning, coding, math, and agentic tasks. ⚠️ Note: privacy and logging guarantees may be limited.
- Reasoning
- Input
- Text
- Output
- Text
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $0.75
- Output
- $3.00
- Cache read
- $0.75
Reference prices as published by the model provider. API example
Specifications
- Context window
- 119K
- Max output
- 64K
Side by side
ERNIE 5.1 Thinking compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| ERNIE 5.1 ThinkingbaiduThis model | Doubao Seed 2.0 Code PreviewdoubaoRemove | |
|---|---|---|
| Provider | baidu | doubao |
| Discovery tier | Balanced | Balanced |
| Added | May 10, 2026 | Feb 14, 2026 |
| Limits | ||
| Context window | 119K | 256KBest |
| Max output | 64K | 128KBest |
| Pricing, USD per 1M tokens | ||
| Input | $0.75Best | $0.78 |
| Output | $3.00Best | $3.89 |
| Cache read | $0.75 | — |
| Capabilities | ||
| Reasoning | Yes | No |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
There are no public benchmark results for these models yet.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "ernie-5.1:thinking",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="ernie-5.1:thinking",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)baidu
Related models
Other baidu models, starting with the same family.