GPT-4.1
Multimodal
by OpenAI
+
+
+
+
About
GPT-4.1, released by OpenAI in April 2025, was designed around the practical needs of software developers — with improvements in precise instruction following, code generation, and a million-token context window optimized for processing large codebases in a single pass. It represented OpenAI's response to growing developer demand for models that reliably follow complex, multi-step instructions without drift across long conversations.
+
+
+
+
Pricing Range
Input (per 1M)$2.00 -$2.00
Output (per 1M)$8.00 -$8.00
Providers1
+
+
+
+
Timeline
ReleasedApr 14, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
2 benchmarks
Average Score
29.2%
Best Score
54.7%
High Performers (80%+)
0Performance Metrics
Max Context Window
1.0MTop Categories
Agents
29.2%
+
+
+
+
All Benchmark Results for GPT-4.1
Complete list of benchmark scores with detailed information
| τ-bench | Agents | 54.70 | 54.7% | Unverified | |
| BrowseComp | Agents | 3.60 | 3.6% | Unverified |