OpenAI logo

GPT-4.1

openai/gpt-4.1

Long-lived GPT workhorse for coding, instruction following, and production apps

Source-linkedgptClosed weightsReleased 2025-04-14
Report data
Context window1.04758M
Maximum output32.768K
Provider offers22
Knowledge cutoff2024-04
Capabilities

What this model supports

ReasoningNo
Tool callingYes
Structured outputYes
AttachmentsYes
Temperature controlYes
Open weightsNo
Creator
OpenAI
Family
gpt
Modalities
Image, Pdf, Text
License
Not documented
Release date
2025-04-14
Model ID
openai/gpt-4.1
Market availability

Provider pricing

Report price →
Providers offering GPT-4.1
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
GitHub Modelsopenai/gpt-4.1128K$0.000$0.000· T ·
View
{
  "input": 0,
  "output": 0
}
Model Oracle AIgpt-4.11.04758M· T S
View
{}
AnyAPIopenai/gpt-4.11.04758M· T S
View
{}
Snowflake Cortexopenai-gpt-4.11.04758M· T S
View
{}
Poeopenai/gpt-4.11.04758M$1.800$7.200$0.450· T ·
View
{
  "cache_read": 0.45,
  "input": 1.8,
  "output": 7.2
}
OrcaRouteropenai/gpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
NEAR AI Cloudopenai/gpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Pioneergpt-4.11.04758M$2.000$8.000$1.000R T S
View
{
  "cache_read": 1,
  "cache_write": 2,
  "input": 2,
  "output": 8
}
Azuregpt-4.11.04758M$2.000$8.000$0.500· T ·
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Kilo Gatewayopenai/gpt-4.11.04758M$2.000$8.000$0.500· T ·
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
OpenRouteropenai/gpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
FastRouteropenai/gpt-4.11.04758M$2.000$8.000$0.500· T ·
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
GitHub Copilotgpt-4.1128K$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Azure Cognitive Servicesgpt-4.11.04758M$2.000$8.000$0.500· T ·
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Abacusgpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
LLM Gatewaygpt-4.11M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Requestyopenai/gpt-4.11.04758M$2.000$8.000$0.500· T ·
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
NanoGPTopenai/gpt-4.11.04758M$2.000$8.000· T S
View
{
  "input": 2,
  "output": 8
}
Vercel AI Gatewayopenai/gpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
DigitalOceanopenai-gpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
OpenAIgpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Merge Gatewayopenai/gpt-4.11.04758M$2.000$8.000$0.500· T S
View
{
  "cache_read": 0.5,
  "input": 2,
  "output": 8
}
Evidence

Published benchmark results

Aider Polyglot vs top 8 models
GPT-5
88.0
o3-pro
84.9
Gemini 2.5 Pro
83.1
o3
81.3
DeepSeek Reasoner
74.2
Claude Opus 4
72.0
o4-mini
72.0
GPT-4.1
52.4
Design Arena: 3d vs top 8 models
Z.ai: GLM 5.2
1371.0
Claude Fable 5
1361.0
xAI: Grok 4.5
1352.0
Kimi K2.6
1348.0
Anthropic: Claude Opus 4.6
1348.0
Z.ai: GLM 5.1
1336.0
DeepSeek V4 Pro
1326.0
GPT-4.1
922.0
Design Arena: codecategories vs top 8 models
Z.ai: GLM 5.2
1352.0
Claude Fable 5
1344.0
Anthropic: Claude Opus 4.6
1336.0
Anthropic: Claude Opus 4.7
1330.0
xAI: Grok 4.5
1328.0
Z.ai: GLM 5.1
1321.0
Kimi K2.6
1320.0
GPT-4.1
1068.0
Design Arena: dataviz vs top 8 models
Claude Fable 5
1372.0
Z.ai: GLM 5.1
1366.0
xAI: Grok 4.5
1330.0
Anthropic: Claude Opus 4.6
1321.0
Anthropic: Claude Opus 4.7
1320.0
Z.ai: GLM 5.2
1318.0
Anthropic: Claude Sonnet 4.6
1317.0
GPT-4.1
1143.0
Design Arena: gamedev vs top 8 models
Claude Fable 5
1387.0
Z.ai: GLM 5.2
1354.0
Claude Sonnet 5
1345.0
GPT-5.5
1344.0
Anthropic: Claude Opus 4.6
1339.0
MiMo-V2.5-Pro
1334.0
Anthropic: Claude Opus 4.7
1334.0
GPT-4.1
1140.0
Design Arena: uicomponent vs top 8 models
Claude Fable 5
1406.0
Anthropic: Claude Opus 4.7
1358.0
Anthropic: Claude Opus 4.6
1344.0
Z.ai: GLM 5.2
1336.0
Qwen: Qwen3.7 Max
1331.0
Z.ai: GLM 5.1
1330.0
Anthropic: Claude Sonnet 4.6
1321.0
GPT-4.1
1050.0
Design Arena: website vs top 8 models
Z.ai: GLM 5.2
1346.0
Claude Fable 5
1336.0
Anthropic: Claude Opus 4.6
1331.0
Anthropic: Claude Opus 4.7
1329.0
xAI: Grok 4.5
1323.0
Anthropic: Claude Sonnet 4.6
1320.0
Claude Sonnet 5
1314.0
GPT-4.1
1074.0