GPT-4.1
GPTBalanced
Tool UseVisionStructured Output
About this model
GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...
Performance Tier
Balanced
GPT-4.1 is a balanced model from GPT : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $2.00 |
| Output (completion) | $8.00 |
| Cache read | $0.500 |
Capabilities
Context Length1.0M
Max Output Tokens—
TokenizerGPT
Inputimage, text, file
Outputtext
Release DateApril 14, 2025
Benchmarks
General Intelligence
MMLU
87.2%
Mathematics
MATH-500
78%
Programming
HumanEval
90.2%
SWE-bench Verified
54.6%
Reasoning
Humanity's Last Exam
5.4%
Recommended Use Cases
CodingGeneral ChatAnalysisData Extraction
Strengths
- Reliable general-purpose model with strong instruction following
- Large 1M token context window
- Good code generation abilities (HumanEval 90.2%)
- Competitive pricing for its capability level
Limitations
- Surpassed by GPT-5 family on most benchmarks
- No native reasoning/thinking mode
Resources
This model may use your data for training