o4 Mini

openai/o4-mini-2025-04-16

OpenAI: o4 Mini, released on 2024-06-01, accepts image, text, and file inputs and produces text output. It provides a context length of 200,000 tokens, supports tool use and reasoning, and its weights are not open. Pricing is $1.1 per million input tokens and $4.4 per million

  • tool use
  • structured outputs
  • reasoning

At a glance

provideropenai
releasedJun 1, 2024
context200K
input / M$1.10

Specifications

What the API gives you

Context window
200K tokens
Max output
100K tokens
Input price
$1.10 / 1M tokens
Output price
$4.40 / 1M tokens
Cache read
$0.28 / 1M tokens
Modalities
image, text, file → text
Knowledge cutoff
Jun 30, 2024
Released
Jun 1, 2024

Measured evidence

Public benchmark record

Aider Polyglot
72%2026-07-17
Aider Polyglot
72%2026-07-21
Aider Polyglot
72%2026-07-23
Aider Polyglot
72%2026-07-27
Aider Polyglot
72%2026-07-28
Aider Polyglot
72%2026-07-29
BFCL
53.2%2026-07-28
BFCL
53.2%2026-07-27
BFCL
53.2%2026-07-29
BFCL
53.2%2026-07-31
BFCL
53.2%2026-07-30
BFCL
53.2%2026-08-02
BFCL
53.2%2026-08-01
BFCL
53.2%2026-08-05
BFCL
53.2%2026-08-03
BFCL
53.2%2026-08-09
BFCL
53.2%2026-08-04
BFCL
53.2%2026-08-06
BFCL
53.2%2026-08-07
BFCL
53.2%2026-08-14
BFCL
53.2%2026-08-10
BFCL
53.2%2026-08-08
BFCL
53.2%2026-08-11
BFCL
53.2%2026-08-18
BFCL
53.2%2026-08-15
BFCL
53.2%2026-08-12
BFCL
53.2%2026-08-13
BFCL
53.2%2026-08-19
BFCL
53.2%2026-08-16
BFCL
53.2%2026-08-20
BFCL
53.2%2026-08-27
BFCL
53.2%2026-08-17
BFCL
53.2%2026-08-21
BFCL
53.2%2026-08-22
BFCL
53.2%2026-08-23
BFCL
53.2%2026-08-24
BFCL
53.2%2026-09-05
BFCL
53.2%2026-08-28
BFCL
53.2%2026-08-25
BFCL
53.2%2026-08-26
BFCL
53.2%2026-09-06
BFCL
53.2%2026-08-29
BFCL
53.2%2026-08-30
BFCL
53.2%2026-08-31
BFCL
53.2%2026-09-01
BFCL
53.2%2026-09-02
BFCL
53.2%2026-09-03
BFCL
53.2%2026-09-04
Design Arena Coding
1006 Elo2026-07-28
Design Arena Coding
1006 Elo2026-07-27
Design Arena Coding
1006 Elo2026-07-30
Design Arena Coding
1006 Elo2026-07-29
Design Arena Coding
1006 Elo2026-07-31
Design Arena Coding
1005 Elo2026-08-02
Design Arena Coding
1004 Elo2026-08-05
Design Arena Coding
1005 Elo2026-08-01
Design Arena Coding
1004 Elo2026-08-09
Design Arena Coding
1005 Elo2026-08-03
Design Arena Coding
1005 Elo2026-08-04
Design Arena Coding
1001 Elo2026-08-14
Design Arena Coding
1005 Elo2026-08-06
Design Arena Coding
1003 Elo2026-08-10
Design Arena Coding
1005 Elo2026-08-07
Design Arena Coding
995 Elo2026-08-18
Design Arena Coding
1004 Elo2026-08-08
Design Arena Coding
995 Elo2026-08-15
Design Arena Coding
1004 Elo2026-08-11
Design Arena Coding
1003 Elo2026-08-12
Design Arena Coding
1001 Elo2026-08-13
Design Arena Coding
994 Elo2026-08-19
Design Arena Coding
1000 Elo2026-08-27
Design Arena Coding
994 Elo2026-08-20
Design Arena Coding
995 Elo2026-08-16
Design Arena Coding
992 Elo2026-09-05
Design Arena Coding
995 Elo2026-08-17
Design Arena Coding
1000 Elo2026-08-21
Design Arena Coding
1000 Elo2026-08-22
Design Arena Coding
1000 Elo2026-08-23
Design Arena Coding
1000 Elo2026-08-28
Design Arena Coding
1001 Elo2026-08-24
Design Arena Coding
1001 Elo2026-08-25
Design Arena Coding
1001 Elo2026-08-26
Design Arena Coding
992 Elo2026-09-06
Design Arena Coding
1000 Elo2026-08-29
Design Arena Coding
999 Elo2026-08-30
Design Arena Coding
999 Elo2026-08-31
Design Arena Coding
1000 Elo2026-09-01
Design Arena Coding
998 Elo2026-09-02
Design Arena Coding
996 Elo2026-09-03
Design Arena Coding
995 Elo2026-09-04
Design Arena UI
1020 Elo2026-07-28
Design Arena UI
1021 Elo2026-07-27
Design Arena UI
1021 Elo2026-07-30
Design Arena UI
1021 Elo2026-07-29
Design Arena UI
1020 Elo2026-07-31
Design Arena UI
1021 Elo2026-08-02
Design Arena UI
1021 Elo2026-08-01
Design Arena UI
1019 Elo2026-08-05
Design Arena UI
1021 Elo2026-08-03
Design Arena UI
1016 Elo2026-08-09
Design Arena UI
1020 Elo2026-08-04
Design Arena UI
1015 Elo2026-08-14
Design Arena UI
1019 Elo2026-08-06
Design Arena UI
1019 Elo2026-08-07
Design Arena UI
1017 Elo2026-08-10
Design Arena UI
1017 Elo2026-08-08
Design Arena UI
1011 Elo2026-08-18
Design Arena UI
1017 Elo2026-08-11
Design Arena UI
1012 Elo2026-08-15
Design Arena UI
1017 Elo2026-08-12
Design Arena UI
1017 Elo2026-08-13
Design Arena UI
1011 Elo2026-08-19
Design Arena UI
1012 Elo2026-08-16
Design Arena UI
1011 Elo2026-08-20
Design Arena UI
1009 Elo2026-08-27
Design Arena UI
1011 Elo2026-08-17
Design Arena UI
1006 Elo2026-09-05
Design Arena UI
1010 Elo2026-08-21
Design Arena UI
1010 Elo2026-08-22
Design Arena UI
1010 Elo2026-08-23
Design Arena UI
1010 Elo2026-08-24
Design Arena UI
1009 Elo2026-08-28
Design Arena UI
1011 Elo2026-08-25
Design Arena UI
1011 Elo2026-08-26
Design Arena UI
1006 Elo2026-09-06
Design Arena UI
1010 Elo2026-08-29
Design Arena UI
1010 Elo2026-08-30
Design Arena UI
1010 Elo2026-08-31
Design Arena UI
1009 Elo2026-09-01
Design Arena UI
1009 Elo2026-09-02
Design Arena UI
1007 Elo2026-09-03
Design Arena UI
1005 Elo2026-09-04
Design Arena Website
1010 Elo2026-07-28
Design Arena Website
1010 Elo2026-07-30
Design Arena Website
1010 Elo2026-07-27
Design Arena Website
1010 Elo2026-07-29
Design Arena Website
1009 Elo2026-07-31
Design Arena Website
1009 Elo2026-08-02
Design Arena Website
1009 Elo2026-08-01
Design Arena Website
1008 Elo2026-08-05
Design Arena Website
1009 Elo2026-08-03
Design Arena Website
1007 Elo2026-08-09
Design Arena Website
1009 Elo2026-08-04
Design Arena Website
1005 Elo2026-08-14
Design Arena Website
1008 Elo2026-08-06
Design Arena Website
1009 Elo2026-08-07
Design Arena Website
1007 Elo2026-08-10
Design Arena Website
1007 Elo2026-08-08
Design Arena Website
996 Elo2026-08-18
Design Arena Website
1007 Elo2026-08-11
Design Arena Website
996 Elo2026-08-15
Design Arena Website
1007 Elo2026-08-12
Design Arena Website
1005 Elo2026-08-13
Design Arena Website
996 Elo2026-08-19
Design Arena Website
996 Elo2026-08-16
Design Arena Website
996 Elo2026-08-20
Design Arena Website
1005 Elo2026-08-27
Design Arena Website
996 Elo2026-08-17
Design Arena Website
1001 Elo2026-09-05
Design Arena Website
1005 Elo2026-08-21
Design Arena Website
1005 Elo2026-08-22
Design Arena Website
1005 Elo2026-08-23
Design Arena Website
1005 Elo2026-08-24
Design Arena Website
1005 Elo2026-08-28
Design Arena Website
1005 Elo2026-08-25
Design Arena Website
1005 Elo2026-08-26
Design Arena Website
998 Elo2026-09-06
Design Arena Website
1005 Elo2026-08-29
Design Arena Website
1004 Elo2026-08-30
Design Arena Website
1004 Elo2026-08-31
Design Arena Website
1004 Elo2026-09-01
Design Arena Website
1003 Elo2026-09-02
Design Arena Website
1001 Elo2026-09-03
Design Arena Website
1001 Elo2026-09-04
LMArena Creative Writing
1296 Elo2026-07-21
LMArena Creative Writing
1296 Elo2026-07-27
LMArena Creative Writing
1296 Elo2026-07-30
LMArena Creative Writing
1296 Elo2026-08-02
LMArena Creative Writing
1296 Elo2026-08-03
LMArena Creative Writing
1295 Elo2026-08-06
LMArena Creative Writing
1295 Elo2026-08-12
LMArena Creative Writing
1295 Elo2026-08-21
LMArena Creative Writing
1294 Elo2026-09-02
LMArena Creative Writing
1294 Elo2026-08-27
LMArena Creative Writing
1294 Elo2026-09-01
LMArena Long Query
1315 Elo2026-07-21
LMArena Long Query
1315 Elo2026-07-27
LMArena Long Query
1315 Elo2026-07-30
LMArena Long Query
1315 Elo2026-08-02
LMArena Long Query
1315 Elo2026-08-03
LMArena Long Query
1315 Elo2026-08-06
LMArena Long Query
1314 Elo2026-08-12
LMArena Long Query
1314 Elo2026-08-21
LMArena Long Query
1314 Elo2026-09-02
LMArena Long Query
1314 Elo2026-08-27
LMArena Long Query
1314 Elo2026-09-01
LMArena Math
1387 Elo2026-07-21
LMArena Math
1387 Elo2026-07-27
LMArena Math
1387 Elo2026-07-30
LMArena Math
1387 Elo2026-08-02
LMArena Math
1387 Elo2026-08-03
LMArena Math
1387 Elo2026-08-06
LMArena Math
1387 Elo2026-08-12
LMArena Math
1387 Elo2026-08-21
LMArena Math
1389 Elo2026-09-01
LMArena Math
1389 Elo2026-08-27
LMArena Text
1390 Elo2026-07-21
LMArena Text
1390 Elo2026-07-27
LMArena Text
1390 Elo2026-07-30
LMArena Text
1390 Elo2026-08-10
LMArena Text
1390 Elo2026-08-02
LMArena Text
1390 Elo2026-08-06
LMArena Text
1390 Elo2026-08-03
LMArena Text
1390 Elo2026-08-21
LMArena Text
1390 Elo2026-08-12
LMArena Text
1391 Elo2026-09-01
LMArena Text
1391 Elo2026-09-02
LMArena Text
1391 Elo2026-08-27
LMArena Vision
1195 Elo2026-07-12
LMArena Vision
1201 Elo2026-07-21
LMArena Vision
1202 Elo2026-07-26
LMArena Vision
1202 Elo2026-07-30
LMArena Vision
1202 Elo2026-08-02
LMArena Vision
1202 Elo2026-08-06
LMArena Vision
1201 Elo2026-08-21
LMArena Vision
1200 Elo2026-08-27
SWE-bench Verified
74.4%2025-06-03
SWE-bench Verified
64.6%2025-05-03
SWE-rebench
27.5% ± 0.62025-12-01tools

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.