GPT-4.1

openai/gpt-4.1-2025-04-14

OpenAI's GPT-4.1, released on 2025‑04‑14, accepts image, text, and file inputs and produces text output. It supports tool integration, does not include built‑in reasoning, and offers a context length of 1,047,576 tokens. Pricing is $2 per million input tokens and $8 per million output tokens; the model’s weights are not open‑source.

  • tool use
  • structured outputs

At a glance

provideropenai
releasedApr 14, 2025
context1.0M
input / M$2

Specifications

What the API gives you

Context window
1.0M tokens
Max output
33K tokens
Input price
$2 / 1M tokens
Output price
$8 / 1M tokens
Cache read
$0.50 / 1M tokens
Modalities
image, text, file → text
Knowledge cutoff
Jun 30, 2024
Released
Apr 14, 2025

Measured evidence

Public benchmark record

Aider Polyglot
52.4%2026-07-17
Aider Polyglot
52.4%2026-07-21
Aider Polyglot
52.4%2026-07-23
Aider Polyglot
52.4%2026-07-28
Aider Polyglot
52.4%2026-07-27
Aider Polyglot
52.4%2026-07-29
Aider Polyglot
52.4%2026-07-30
Aider Polyglot
52.4%2026-07-31
Aider Polyglot
52.4%2026-08-01
Aider Polyglot
52.4%2026-08-02
Aider Polyglot
52.4%2026-08-05
Aider Polyglot
52.4%2026-08-03
Aider Polyglot
52.4%2026-08-09
Aider Polyglot
52.4%2026-08-04
Aider Polyglot
52.4%2026-08-06
Aider Polyglot
52.4%2026-08-07
Aider Polyglot
52.4%2026-08-14
Aider Polyglot
52.4%2026-08-08
Aider Polyglot
52.4%2026-08-10
Aider Polyglot
52.4%2026-08-15
Aider Polyglot
52.4%2026-08-11
Aider Polyglot
52.4%2026-08-18
Aider Polyglot
52.4%2026-08-12
Aider Polyglot
52.4%2026-08-19
Aider Polyglot
52.4%2026-08-13
Aider Polyglot
52.4%2026-08-20
Aider Polyglot
52.4%2026-08-16
Aider Polyglot
52.4%2026-08-17
Aider Polyglot
52.4%2026-08-21
Aider Polyglot
52.4%2026-08-27
Aider Polyglot
52.4%2026-08-22
Aider Polyglot
52.4%2026-08-23
Aider Polyglot
52.4%2026-08-24
Aider Polyglot
52.4%2026-08-25
Aider Polyglot
52.4%2026-09-05
Aider Polyglot
52.4%2026-08-26
Aider Polyglot
52.4%2026-08-28
Aider Polyglot
52.4%2026-09-06
Aider Polyglot
52.4%2026-08-29
Aider Polyglot
52.4%2026-08-30
Aider Polyglot
52.4%2026-08-31
Aider Polyglot
52.4%2026-09-01
Aider Polyglot
52.4%2026-09-02
Aider Polyglot
52.4%2026-09-03
Aider Polyglot
52.4%2026-09-04
BFCL
54.0%2026-07-28
BFCL
54.0%2026-07-27
BFCL
54.0%2026-07-29
BFCL
54.0%2026-07-31
BFCL
54.0%2026-07-30
BFCL
54.0%2026-08-02
BFCL
54.0%2026-08-01
BFCL
54.0%2026-08-05
BFCL
54.0%2026-08-03
BFCL
54.0%2026-08-09
BFCL
54.0%2026-08-04
BFCL
54.0%2026-08-06
BFCL
54.0%2026-08-07
BFCL
54.0%2026-08-14
BFCL
54.0%2026-08-10
BFCL
54.0%2026-08-08
BFCL
54.0%2026-08-18
BFCL
54.0%2026-08-11
BFCL
54.0%2026-08-15
BFCL
54.0%2026-08-12
BFCL
54.0%2026-08-13
BFCL
54.0%2026-08-19
BFCL
54.0%2026-08-16
BFCL
54.0%2026-08-20
BFCL
54.0%2026-08-27
BFCL
54.0%2026-08-17
BFCL
54.0%2026-08-21
BFCL
54.0%2026-08-22
BFCL
54.0%2026-08-23
BFCL
54.0%2026-08-24
BFCL
54.0%2026-09-05
BFCL
54.0%2026-08-28
BFCL
54.0%2026-08-25
BFCL
54.0%2026-08-26
BFCL
54.0%2026-09-06
BFCL
54.0%2026-08-29
BFCL
54.0%2026-08-30
BFCL
54.0%2026-08-31
BFCL
54.0%2026-09-01
BFCL
54.0%2026-09-02
BFCL
54.0%2026-09-03
BFCL
54.0%2026-09-04
Design Arena Coding
1056 Elo2026-07-28
Design Arena Coding
1056 Elo2026-07-27
Design Arena Coding
1056 Elo2026-07-30
Design Arena Coding
1056 Elo2026-07-29
Design Arena Coding
1056 Elo2026-07-31
Design Arena Coding
1055 Elo2026-08-02
Design Arena Coding
1054 Elo2026-08-05
Design Arena Coding
1055 Elo2026-08-01
Design Arena Coding
1053 Elo2026-08-09
Design Arena Coding
1055 Elo2026-08-03
Design Arena Coding
1055 Elo2026-08-04
Design Arena Coding
1050 Elo2026-08-14
Design Arena Coding
1054 Elo2026-08-06
Design Arena Coding
1053 Elo2026-08-10
Design Arena Coding
1055 Elo2026-08-07
Design Arena Coding
1044 Elo2026-08-18
Design Arena Coding
1054 Elo2026-08-08
Design Arena Coding
1045 Elo2026-08-15
Design Arena Coding
1053 Elo2026-08-11
Design Arena Coding
1052 Elo2026-08-12
Design Arena Coding
1051 Elo2026-08-13
Design Arena Coding
1043 Elo2026-08-19
Design Arena Coding
1050 Elo2026-08-27
Design Arena Coding
1043 Elo2026-08-20
Design Arena Coding
1044 Elo2026-08-16
Design Arena Coding
1042 Elo2026-09-05
Design Arena Coding
1044 Elo2026-08-17
Design Arena Coding
1050 Elo2026-08-21
Design Arena Coding
1050 Elo2026-08-22
Design Arena Coding
1050 Elo2026-08-23
Design Arena Coding
1050 Elo2026-08-28
Design Arena Coding
1050 Elo2026-08-24
Design Arena Coding
1050 Elo2026-08-25
Design Arena Coding
1051 Elo2026-08-26
Design Arena Coding
1042 Elo2026-09-06
Design Arena Coding
1050 Elo2026-08-29
Design Arena Coding
1049 Elo2026-08-30
Design Arena Coding
1049 Elo2026-08-31
Design Arena Coding
1049 Elo2026-09-01
Design Arena Coding
1048 Elo2026-09-02
Design Arena Coding
1046 Elo2026-09-03
Design Arena Coding
1045 Elo2026-09-04
Design Arena UI
1037 Elo2026-07-28
Design Arena UI
1038 Elo2026-07-27
Design Arena UI
1037 Elo2026-07-30
Design Arena UI
1037 Elo2026-07-29
Design Arena UI
1037 Elo2026-07-31
Design Arena UI
1037 Elo2026-08-02
Design Arena UI
1037 Elo2026-08-01
Design Arena UI
1036 Elo2026-08-05
Design Arena UI
1037 Elo2026-08-03
Design Arena UI
1033 Elo2026-08-09
Design Arena UI
1036 Elo2026-08-04
Design Arena UI
1031 Elo2026-08-14
Design Arena UI
1036 Elo2026-08-06
Design Arena UI
1035 Elo2026-08-07
Design Arena UI
1033 Elo2026-08-10
Design Arena UI
1034 Elo2026-08-08
Design Arena UI
1028 Elo2026-08-18
Design Arena UI
1033 Elo2026-08-11
Design Arena UI
1029 Elo2026-08-15
Design Arena UI
1034 Elo2026-08-12
Design Arena UI
1034 Elo2026-08-13
Design Arena UI
1028 Elo2026-08-19
Design Arena UI
1028 Elo2026-08-16
Design Arena UI
1028 Elo2026-08-20
Design Arena UI
1026 Elo2026-08-27
Design Arena UI
1028 Elo2026-08-17
Design Arena UI
1022 Elo2026-09-05
Design Arena UI
1027 Elo2026-08-21
Design Arena UI
1027 Elo2026-08-22
Design Arena UI
1027 Elo2026-08-23
Design Arena UI
1027 Elo2026-08-24
Design Arena UI
1026 Elo2026-08-28
Design Arena UI
1027 Elo2026-08-25
Design Arena UI
1027 Elo2026-08-26
Design Arena UI
1023 Elo2026-09-06
Design Arena UI
1026 Elo2026-08-29
Design Arena UI
1027 Elo2026-08-30
Design Arena UI
1026 Elo2026-08-31
Design Arena UI
1026 Elo2026-09-01
Design Arena UI
1026 Elo2026-09-02
Design Arena UI
1024 Elo2026-09-03
Design Arena UI
1022 Elo2026-09-04
Design Arena Website
1063 Elo2026-07-28
Design Arena Website
1063 Elo2026-07-30
Design Arena Website
1063 Elo2026-07-27
Design Arena Website
1063 Elo2026-07-29
Design Arena Website
1063 Elo2026-07-31
Design Arena Website
1062 Elo2026-08-02
Design Arena Website
1062 Elo2026-08-01
Design Arena Website
1062 Elo2026-08-05
Design Arena Website
1062 Elo2026-08-03
Design Arena Website
1061 Elo2026-08-09
Design Arena Website
1062 Elo2026-08-04
Design Arena Website
1058 Elo2026-08-14
Design Arena Website
1062 Elo2026-08-06
Design Arena Website
1062 Elo2026-08-07
Design Arena Website
1061 Elo2026-08-10
Design Arena Website
1061 Elo2026-08-08
Design Arena Website
1050 Elo2026-08-18
Design Arena Website
1061 Elo2026-08-11
Design Arena Website
1050 Elo2026-08-15
Design Arena Website
1060 Elo2026-08-12
Design Arena Website
1059 Elo2026-08-13
Design Arena Website
1050 Elo2026-08-19
Design Arena Website
1049 Elo2026-08-16
Design Arena Website
1050 Elo2026-08-20
Design Arena Website
1058 Elo2026-08-27
Design Arena Website
1050 Elo2026-08-17
Design Arena Website
1054 Elo2026-09-05
Design Arena Website
1058 Elo2026-08-21
Design Arena Website
1058 Elo2026-08-22
Design Arena Website
1059 Elo2026-08-23
Design Arena Website
1059 Elo2026-08-24
Design Arena Website
1058 Elo2026-08-28
Design Arena Website
1059 Elo2026-08-25
Design Arena Website
1059 Elo2026-08-26
Design Arena Website
1052 Elo2026-09-06
Design Arena Website
1058 Elo2026-08-29
Design Arena Website
1058 Elo2026-08-30
Design Arena Website
1058 Elo2026-08-31
Design Arena Website
1058 Elo2026-09-01
Design Arena Website
1057 Elo2026-09-02
Design Arena Website
1055 Elo2026-09-03
Design Arena Website
1054 Elo2026-09-04
LMArena Creative Writing
1364 Elo2026-07-21
LMArena Creative Writing
1364 Elo2026-07-27
LMArena Creative Writing
1364 Elo2026-07-30
LMArena Creative Writing
1364 Elo2026-08-02
LMArena Creative Writing
1364 Elo2026-08-03
LMArena Creative Writing
1363 Elo2026-08-06
LMArena Creative Writing
1363 Elo2026-08-12
LMArena Creative Writing
1363 Elo2026-08-21
LMArena Creative Writing
1364 Elo2026-09-02
LMArena Creative Writing
1364 Elo2026-08-27
LMArena Creative Writing
1364 Elo2026-09-01
LMArena Long Query
1383 Elo2026-07-21
LMArena Long Query
1383 Elo2026-07-27
LMArena Long Query
1383 Elo2026-07-30
LMArena Long Query
1383 Elo2026-08-02
LMArena Long Query
1383 Elo2026-08-06
LMArena Long Query
1383 Elo2026-08-03
LMArena Long Query
1384 Elo2026-08-12
LMArena Long Query
1383 Elo2026-08-21
LMArena Long Query
1384 Elo2026-09-02
LMArena Long Query
1385 Elo2026-08-27
LMArena Long Query
1384 Elo2026-09-01
LMArena Math
1367 Elo2026-07-21
LMArena Math
1367 Elo2026-07-27
LMArena Math
1367 Elo2026-07-30
LMArena Math
1368 Elo2026-08-02
LMArena Math
1368 Elo2026-08-03
LMArena Math
1368 Elo2026-08-06
LMArena Math
1368 Elo2026-08-12
LMArena Math
1368 Elo2026-08-21
LMArena Math
1369 Elo2026-09-01
LMArena Math
1368 Elo2026-08-27
LMArena Text
1414 Elo2026-07-21
LMArena Text
1414 Elo2026-07-27
LMArena Text
1414 Elo2026-07-30
LMArena Text
1414 Elo2026-08-10
LMArena Text
1414 Elo2026-08-02
LMArena Text
1414 Elo2026-08-06
LMArena Text
1414 Elo2026-08-03
LMArena Text
1414 Elo2026-08-21
LMArena Text
1414 Elo2026-08-12
LMArena Text
1414 Elo2026-09-01
LMArena Text
1414 Elo2026-09-02
LMArena Text
1414 Elo2026-08-27
LMArena Vision
1210 Elo2026-07-12
LMArena Vision
1214 Elo2026-07-21
LMArena Vision
1214 Elo2026-07-26
LMArena Vision
1214 Elo2026-07-30
LMArena Vision
1214 Elo2026-08-02
LMArena Vision
1214 Elo2026-08-06
LMArena Vision
1214 Elo2026-08-21
LMArena Vision
1214 Elo2026-08-27
SWE-bench Verified
74.6%2025-09-15
SWE-rebench
30.1% ± 0.22025-08-01text
SWE-rebench
29.7% ± 0.72025-12-01tools

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • 70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    56% of intended weighted task evidence across 4 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 8 of 8 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    56% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 3 of 4 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • 50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Competition MathProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    23% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • 20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.

  • 18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • 13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.