GPT 4.1
OpenAI
openai/gpt-4.1
200K context flagship
Context Window
200K
200,000 tokens
Max Output
33K
32,768 tokens
About this model
GPT-4.1 is OpenAI's high-performance general-purpose model with a 200K token context window. It excels at complex reasoning and programming while supporting vision understanding.
As the successor to GPT-4o, GPT-4.1 achieves significant improvements on the SWE-bench programming benchmark and is a top choice for professional developers. More affordable than GPT-5, it's suitable for most production use cases.
Highlights
200K context
SWE-bench leader
Vision support
Great value
Best For
Production API callsCode generation & debuggingDocument analysisMulti-turn conversation
2025-04-14TransformerProprietary
Capabilities
ChatVisionCodepdftoolscache
Aliases
gpt-4.1Pricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $2.10 |
| Output / 1M | $8.40 |
| Cache Read | $0.53 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="openai/gpt-4.1", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)