GPT-5.1
GPTBalanced
ThinkingTool UseVisionStructured Output
About this model
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
Performance Tier
Balanced
GPT-5.1 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 plansHigh
High pricing. Reserve this level for tasks that demand maximum quality.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $1.25 |
| Output (completion) | $10.00 |
| Cache read | $0.130 |
Capabilities
Context Length400K
Max Output Tokens128K
TokenizerGPT
Inputimage, text, file
Outputtext
Release DateNovember 13, 2025
Benchmarks
General Intelligence
MMLU
90.2%
GPQA Diamond
85.2%
Mathematics
MATH-500
90.8%
AIME 2025
94%
Programming
HumanEval
94.5%
SWE-bench Verified
72%
Recommended Use Cases
CodingAnalysisResearchGeneral ChatMathematics
Strengths
- Strong all-around performance across reasoning and coding
- Excellent mathematical reasoning (MATH-500 90.8%)
- Good balance of capability and speed
- Large context window for document analysis
Limitations
- Surpassed by GPT-5.2 on most benchmarks
- Higher cost than GPT-5 Mini for simple tasks
Resources
This model may use your data for training