Back to Models
openai/gpt-4-1
Not Available
GPT-4.1
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 GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.
4/14/2025
1,047,576 tokens
#170 Text (Japanese)
Specifications
Modalities
Input
image
text
file
Output
text
Supported Parameters
max_tokens
response_format
seed
structured_outputs
temperature
tool_choice
tools
top_p
Max Output Tokens
32,768Frequently asked questions
- Is GPT-4.1 available on FastMetal?
- Not at the moment. GPT-5.6 Sol, from the same lab, is available on the FastMetal API today.
- What is the context window of GPT-4.1?
- 1,047,576 tokens, shared between the prompt and the response.
- How does GPT-4.1 rank?
- #170 on the public arena's Japanese board (ELO 1,262). Ranks move as the leaderboard is updated.
Leaderboard
Text
OverallELO: 1,312
#257JapaneseELO: 1,262
#170ChineseELO: 1,314
#248KoreanELO: 1,252
#196EnglishELO: 1,325
#261frenchELO: 1,340
#199germanELO: 1,298
#204spanishELO: 1,311
#208russianELO: 1,300
#245CodingELO: 1,340
#267MathELO: 1,303
#229Creative WritingELO: 1,286
#241Instruction FollowingELO: 1,296
#252Hard PromptsELO: 1,312
#264Multi-TurnELO: 1,298
#255