OpenAI model product
GPT-5.4-mini
4-mini is an OpenAI mini model for coding, computer use, and subagents.
Updated Sep 8, 2026. Default version: GPT-5.4 mini
LLMBoard Score58.9GPT-5.4 mini
Coverage0%15 benchmark families
Context window400KTokens
Official input price$0.75OpenAI API
GPT-5.4-mini Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.4-mini Benchmark Results
Benchmark scores for GPT-5.4 mini.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGraphwalks BFS <128k | Score76.30% | Rank04 | Participants11 | Percentile70.00% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents <128k | Score71.50% | Rank05 | Participants11 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score45.36% | Rank10 | Participants26 | Percentile64.00% | EvidenceB | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score87.37% | Rank12 | Participants18 | Percentile35.29% | EvidenceC | Evaluated |
| BenchmarkLegal Agent Benchmark | Score0.00% | Rank13 | Participants13 | Percentile0.00% | EvidenceB | Evaluated |
| BenchmarkTau2 Telecom | Score93.40% | Rank13 | Participants36 | Percentile65.71% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score33.60% | Rank14 | Participants24 | Percentile43.48% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score72.10% | Rank16 | Participants24 | Percentile34.78% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score60.00% | Rank20 | Participants51 | Percentile62.00% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score76.60% | Rank27 | Participants69 | Percentile61.76% | EvidenceC | Evaluated |
| BenchmarkMCP Atlas | Score57.70% | Rank31 | Participants34 | Percentile9.09% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,252.07 rating | Rank32 | Participants107 | Percentile70.75% | EvidenceA | Evaluated |
| BenchmarkToolathlon | Score42.90% | Rank33 | Participants41 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score54.40% | Rank39 | Participants55 | Percentile29.63% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score88.00% | Rank43 | Participants247 | Percentile82.93% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,245.48 rating | Rank45 | Participants107 | Percentile58.49% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,448.26 rating | Rank46 | Participants121 | Percentile62.50% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score28.20% | Rank55 | Participants103 | Percentile47.06% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,448.20 rating | Rank56 | Participants210 | Percentile73.68% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,397.19 rating | Rank61 | Participants97 | Percentile37.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,412.18 rating | Rank91 | Participants210 | Percentile56.94% | EvidenceA | Evaluated |
GPT-5.4-mini Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision style control | Categoryhomework | Rank22 | Rating / score1,292.58 | Votes3,354 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank24 | Rating / score1,428.15 | Votes716 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank25 | Rating / score1,481.60 | Votes1,677 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank25 | Rating / score1,286.90 | Votes3,354 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryjapanese | Rank27 | Rating / score1,393.18 | Votes406 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank27 | Rating / score1,185.96 | Votes153 | ObservationsN/A | Result date |
| Arenatext factuality | Categorykorean | Rank28 | Rating / score1,394.70 | Votes618 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank29 | Rating / score1,204.55 | Votes153 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank29 | Rating / score1,282.54 | Votes6,468 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank32 | Rating / score1,252.07 | Votes24,076 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry business and management and financial operations | Rank33 | Rating / score1,459.76 | Votes10,157 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank33 | Rating / score1,460.90 | Votes1,164 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank33 | Rating / score1,289.16 | Votes1,355 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank33 | Rating / score1,236.33 | Votes803 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank33 | Rating / score1,263.34 | Votes17,069 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank34 | Rating / score1,461.51 | Votes4,925 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank36 | Rating / score1,446.20 | Votes2,569 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank36 | Rating / score1,248.92 | Votes10,099 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank37 | Rating / score1,463.16 | Votes3,764 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank39 | Rating / score1,264.34 | Votes6,468 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank40 | Rating / score1,289.00 | Votes1,355 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank40 | Rating / score1,234.36 | Votes803 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank41 | Rating / score1,438.67 | Votes31,857 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank41 | Rating / score1,459.59 | Votes12,110 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryhard prompts | Rank42 | Rating / score1,472.54 | Votes38,810 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank42 | Rating / score1,468.29 | Votes11,175 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank42 | Rating / score1,225.34 | Votes1,500 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank43 | Rating / score1,252.79 | Votes17,069 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymulti turn | Rank44 | Rating / score1,460.33 | Votes9,225 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank45 | Rating / score1,454.19 | Votes6,274 | ObservationsN/A | Result date |
GPT-5.4-mini Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.75 input, $4.5 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.375 input, $4 output per 1M via Xpersona
- Tracked offerings
- 37
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDgpt-5-4-mini | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context400K | Updated |
| ProviderXpersona | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.375 | Output / 1M$4 | Context272K | Updated |
| ProviderPoe | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.68 | Output / 1M$4 | Context400K | Updated |
| ProviderOrcaRouter | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderCrossModel | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderDatabricks | Provider model IDdatabricks-gpt-5-4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderOpenAI | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderOpper | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderLLM Gateway | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderVivgrid | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context128K | Updated |
| ProviderFastRouter | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderZenMux | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderFreeModel | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderOfox | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderNeon | Provider model IDgpt-5-4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderAzure Cognitive Services | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| Provider302.AI | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderOpenCode Zen | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderRequesty | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderAzure | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderFrogBot | Provider model IDgpt-5-4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderAIHubMix | Provider model IDgpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-5.4-mini | Regionglobal | Input / 1M$0.75 | Output / 1M$4.5 | Context400K | Updated |
GPT-5.4-mini Runtime Performance
Provider-specific output speed and catalog latency for GPT-5.4 mini. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5.4-mini Specifications
Technical details for the model's default version.
- Version
- GPT-5.4 mini
- Released
- Mar 17, 2026
- Knowledge cutoff
- Aug 31, 2025
- Parameters
- N/A
- Context window
- 400K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5.4-mini Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGPT-5.4 mini | Released | LLMBoard58.88 | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to GPT-5.4-mini
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5.2-Codex
OpenAI
OP
GPT-5.1-Instant
OpenAI
OP
GPT-5.1
OpenAI
OP
GPT-5.3-Codex
OpenAI
OP
GPT-5.5-Instant
OpenAI
OP
o3
OpenAI
What is GPT-5.4-mini?
Key information about GPT-5.4-mini and its available data.
4-mini is an OpenAI large language model designed for high-volume workloads. It supports coding, reasoning, multimodal understanding, computer use, subagents, and tool use.
Data as of 2026-09-08.
FAQ
Common questions about GPT-5.4-mini.
When was GPT-5.4-mini released?
GPT-5.4-mini's default version was released on Mar 17, 2026.
How much does GPT-5.4-mini cost?
GPT-5.4-mini's official API price is $0.75 per million input tokens and $4.5 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.375 input and $4 output via Xpersona.
Who created GPT-5.4-mini?
GPT-5.4-mini was created by OpenAI.
What is the context window for GPT-5.4-mini?
The default version has a 400K token context window.
Is GPT-5.4-mini open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.4-mini?
37 provider offerings are linked to the default version.