GPT-5.4 Mini

openai/gpt-5.4-mini-20260317

OpenAI's GPT-5.4 Mini, released on 2026-03-17, supports file, image, and text inputs and generates text output. It provides a context length of 400,000 tokens, supports tool usage and reasoning, and is not open-weight. Pricing is $0.75 per million input tokens and $4.5 per million output tokens.

  • tool use
  • structured outputs
  • reasoning

At a glance

provideropenai
releasedMar 12, 2026
context400K
input / M$0.75

Specifications

What the API gives you

Context window
400K tokens
Max output
128K tokens
Input price
$0.75 / 1M tokens
Output price
$4.50 / 1M tokens
Cache read
$0.075 / 1M tokens
Modalities
file, image, text → text
Knowledge cutoff
Aug 31, 2025
Released
Mar 12, 2026

Measured evidence

Public benchmark record

LiveBench Coding
71.6%2026-06-25
LiveBench Language
71.0%2026-06-25
LiveBench Math
78.5%2026-06-25
LiveBench Reasoning
71.3%2026-06-25
LMArena Creative Writing
1372 Elo2026-07-21
LMArena Creative Writing
1371 Elo2026-07-27
LMArena Creative Writing
1371 Elo2026-07-30
LMArena Creative Writing
1370 Elo2026-08-02
LMArena Creative Writing
1370 Elo2026-08-03
LMArena Creative Writing
1371 Elo2026-08-06
LMArena Creative Writing
1372 Elo2026-08-12
LMArena Creative Writing
1372 Elo2026-08-21
LMArena Creative Writing
1372 Elo2026-09-02
LMArena Creative Writing
1371 Elo2026-08-27
LMArena Creative Writing
1372 Elo2026-09-01
LMArena Long Query
1408 Elo2026-07-21
LMArena Long Query
1409 Elo2026-07-27
LMArena Long Query
1409 Elo2026-07-30
LMArena Long Query
1409 Elo2026-08-02
LMArena Long Query
1408 Elo2026-08-06
LMArena Long Query
1409 Elo2026-08-03
LMArena Long Query
1409 Elo2026-08-12
LMArena Long Query
1409 Elo2026-08-21
LMArena Long Query
1408 Elo2026-09-02
LMArena Long Query
1408 Elo2026-08-27
LMArena Long Query
1408 Elo2026-09-01
LMArena Math
1419 Elo2026-07-21
LMArena Math
1419 Elo2026-07-27
LMArena Math
1419 Elo2026-07-30
LMArena Math
1419 Elo2026-08-02
LMArena Math
1419 Elo2026-08-03
LMArena Math
1418 Elo2026-08-06
LMArena Math
1419 Elo2026-08-12
LMArena Math
1419 Elo2026-08-21
LMArena Math
1420 Elo2026-09-01
LMArena Math
1420 Elo2026-08-27
LMArena Text
1496 Elo2026-07-20
LMArena Text
1449 Elo2026-07-21
LMArena Text
1449 Elo2026-08-02
LMArena Text
1449 Elo2026-07-27
LMArena Text
1449 Elo2026-07-30
LMArena Text
1449 Elo2026-08-03
LMArena Text
1448 Elo2026-08-10
LMArena Text
1448 Elo2026-08-06
LMArena Text
1448 Elo2026-08-21
LMArena Text
1448 Elo2026-08-12
LMArena Text
1448 Elo2026-09-01
LMArena Text
1448 Elo2026-09-02
LMArena Text
1448 Elo2026-08-27
LMArena Vision
1247 Elo2026-07-12
LMArena Vision
1254 Elo2026-07-21
LMArena Vision
1254 Elo2026-07-26
LMArena Vision
1254 Elo2026-07-30
LMArena Vision
1255 Elo2026-08-02
LMArena Vision
1253 Elo2026-08-06
LMArena Vision
1252 Elo2026-08-21
LMArena Vision
1252 Elo2026-08-27
LMArena WebDev
1398 Elo2026-07-16
LMArena WebDev
1397 Elo2026-07-21
LMArena WebDev
1398 Elo2026-07-20
LMArena WebDev
1399 Elo2026-07-27
LMArena WebDev
1399 Elo2026-07-24
LMArena WebDev
1399 Elo2026-07-28
LMArena WebDev
1399 Elo2026-07-30
LMArena WebDev
1399 Elo2026-08-01
LMArena WebDev
1399 Elo2026-07-31
LMArena WebDev
1399 Elo2026-08-06
LMArena WebDev
1399 Elo2026-08-02
LMArena WebDev
1397 Elo2026-08-12
LMArena WebDev
1398 Elo2026-08-10
LMArena WebDev
1397 Elo2026-08-14
LMArena WebDev
1397 Elo2026-09-01
LMArena WebDev
1397 Elo2026-09-05
LMArena WebDev
1397 Elo2026-08-21
LMArena WebDev
1397 Elo2026-08-30

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

Task evidence

How broad is the support?

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

  • Best LLM for Competition MathEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Business WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • 100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionEstablished evidence

    81% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.

  • 67% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 65% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesEstablished evidence

    64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best Value LLMEstablished evidence

    64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.

  • 55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    44% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or Design Arena Coding. 8 of 8 configured evaluation feeds currently have results.

  • 40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-bench Verified. 6 of 6 configured evaluation feeds currently have results.

  • 40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for Frontend & UIProvisional evidence

    40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Design Arena Coding or Design Arena UI. 5 of 5 configured evaluation feeds currently have results.

  • 39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.

  • 31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 2 of 4 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

    19% 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.

  • 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.

  • Best LLM for Autonomous AgentsProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    15% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 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.

  • Best LLM for Hermes AgentProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 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.