OpenAI model product
GPT-5.4-nano
4-class model for classification, data extraction, ranking, lightweight coding subagents, and other simple high-volume tasks.
Updated Oct 23, 2026. Default version: GPT-5.4 nano
LLMBoard Score47.1GPT-5.4 nano
Coverage80%15 benchmark families
Context window400KTokens
Official input price$0.20OpenAI API
GPT-5.4-nano Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.4-nano Benchmark Results
Benchmark scores for GPT-5.4 nano.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkGraphwalks BFS <128k | Score73.40% | Rank06 | Participants13 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents <128k | Score50.80% | Rank10 | Participants12 | Percentile18.18% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score75.81% | Rank13 | Participants20 | Percentile36.84% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score75.92% | Rank15 | Participants168 | Percentile91.62% | EvidenceB | EvaluatedN/A |
| BenchmarkMRCR v2 (8-needle) | Score33.10% | Rank16 | Participants25 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score92.50% | Rank16 | Participants37 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkLiveBench math (2026-06-25) | Score90.98 score | Rank18 | Participants43 | Percentile59.52% | EvidenceB | EvaluatedN/A |
| BenchmarkFinance Agent v2 | Score38.22% | Rank20 | Participants29 | Percentile32.14% | EvidenceB | Evaluated |
| BenchmarkOSWorld-Verified | Score39.00% | Rank28 | Participants28 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLiveBench instruction (2026-06-25) | Score67.20 score | Rank28 | Participants43 | Percentile35.71% | EvidenceB | EvaluatedN/A |
| BenchmarkLiveBench | Score70.13% | Rank30 | Participants38 | Percentile21.62% | EvidenceB | Evaluated |
| BenchmarkLiveBench reasoning (2026-06-25) | Score81.10 score | Rank30 | Participants43 | Percentile30.95% | EvidenceB | EvaluatedN/A |
| BenchmarkAA CritPt | Score9.25% | Rank36 | Participants200 | Percentile82.41% | EvidenceB | EvaluatedN/A |
| BenchmarkMCP Atlas | Score56.10% | Rank37 | Participants39 | Percentile5.26% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score35.50% | Rank37 | Participants42 | Percentile12.20% | EvidenceC | Evaluated |
| BenchmarkAA SciCode Subtasks | Score47.22% | Rank38 | Participants89 | Percentile57.95% | EvidenceB | EvaluatedN/A |
| BenchmarkTerminal-Bench 2.0 | Score46.30% | Rank42 | Participants53 | Percentile21.15% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score66.10% | Rank47 | Participants73 | Percentile36.11% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score52.40% | Rank52 | Participants63 | Percentile17.74% | EvidenceC | Evaluated |
| BenchmarkAA LCR v1.1 | Score76.67% | Rank54 | Participants193 | Percentile72.40% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score28.27% | Rank59 | Participants200 | Percentile70.85% | EvidenceB | EvaluatedN/A |
| BenchmarkHumanity's Last Exam | Score24.30% | Rank65 | Participants109 | Percentile40.74% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,195.60 rating | Rank76 | Participants113 | Percentile33.04% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,198.84 rating | Rank77 | Participants113 | Percentile32.14% | EvidenceA | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score25.67% | Rank81 | Participants201 | Percentile60.00% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score82.80% | Rank85 | Participants256 | Percentile67.06% | EvidenceC | Evaluated |
| BenchmarkAA GPQA Diamond | Score81.72% | Rank91 | Participants199 | Percentile54.55% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Factuality | Score1,417.22 rating | Rank105 | Participants131 | Percentile20.00% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,401.18 rating | Rank117 | Participants218 | Percentile46.54% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,372.00 rating | Rank130 | Participants218 | Percentile40.55% | EvidenceA | Evaluated |
GPT-5.4-nano Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryjapanese | Rank32 | Rating / score1,391.55 | Votes453 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank33 | Rating / score1,394.45 | Votes549 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank40 | Rating / score1,140.78 | Votes178 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank40 | Rating / score1,116.10 | Votes178 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank49 | Rating / score1,366.67 | Votes737 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank60 | Rating / score1,236.33 | Votes1,739 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank65 | Rating / score1,443.32 | Votes1,671 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank67 | Rating / score1,232.36 | Votes1,739 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank69 | Rating / score1,430.44 | Votes2,745 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank70 | Rating / score1,423.87 | Votes2,643 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank70 | Rating / score1,233.31 | Votes3,429 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank70 | Rating / score1,155.86 | Votes923 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank71 | Rating / score1,400.28 | Votes1,477 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank71 | Rating / score1,161.02 | Votes923 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank72 | Rating / score1,225.14 | Votes3,429 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank72 | Rating / score1,226.32 | Votes6,840 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank73 | Rating / score1,210.47 | Votes6,840 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank73 | Rating / score1,203.79 | Votes18,222 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank74 | Rating / score1,212.65 | Votes18,222 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank75 | Rating / score1,203.55 | Votes10,341 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank76 | Rating / score1,201.67 | Votes10,341 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank76 | Rating / score1,195.60 | Votes25,624 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank77 | Rating / score1,157.77 | Votes1,531 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank77 | Rating / score1,198.84 | Votes25,624 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank78 | Rating / score1,158.73 | Votes1,531 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank83 | Rating / score1,444.86 | Votes5,136 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank84 | Rating / score1,435.40 | Votes3,802 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank85 | Rating / score1,428.09 | Votes3,000 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank85 | Rating / score1,374.56 | Votes610 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank89 | Rating / score1,423.87 | Votes3,947 | ObservationsN/A | Result date |
GPT-5.4-nano Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.20 input, $1.25 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.1818 input, $1.14 output per 1M via Poe
- Tracked offerings
- 35
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.1818 | Output / 1M$1.14 | Context400K | Updated |
| ProviderOrcaRouter | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderCrossModel | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderDatabricks | Provider model IDdatabricks-gpt-5-4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderOpenAI | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderLLM Gateway | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderVivgrid | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context128K | Updated |
| ProviderFastRouter | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderZenMux | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderOfox | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderNeon | Provider model IDgpt-5-4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderAzure Cognitive Services | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| Provider302.AI | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderOpenCode | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderRequesty | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderAzure | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderFrogBot | Provider model IDgpt-5-4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderGitHub Copilot | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
| ProviderPioneer | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context1M | Updated |
| ProviderAbacus | Provider model IDgpt-5.4-nano | Regionglobal | Input / 1M$0.20 | Output / 1M$1.25 | Context400K | Updated |
GPT-5.4-nano Runtime Performance
Provider-specific output speed and catalog latency for GPT-5.4 nano. 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-nano Specifications
Technical details for the model's default version.
- Version
- GPT-5.4 nano
- 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-nano 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 nano | Released | LLMBoard47.12 | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to GPT-5.4-nano
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5
OpenAI
OP
GPT-5.1-Codex
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
GPT-5-Codex
OpenAI
OP
GPT-Rosalind
OpenAI
OP
o3
OpenAI
What is GPT-5.4-nano?
Key information about GPT-5.4-nano and its available data.
4-class model optimized for simple, high-volume tasks. It provides reasoning, multimodal understanding, and tool use for latency-sensitive workloads.
Data as of 2026-10-22.
FAQ
Common questions about GPT-5.4-nano.
When was GPT-5.4-nano released?
GPT-5.4-nano's default version was released on Mar 17, 2026.
How much does GPT-5.4-nano cost?
GPT-5.4-nano's official API price is $0.20 per million input tokens and $1.25 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.1818 input and $1.14 output via Poe.
Who created GPT-5.4-nano?
GPT-5.4-nano was created by OpenAI.
What is the context window for GPT-5.4-nano?
The default version has a 400K token context window.
Is GPT-5.4-nano open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.4-nano?
35 provider offerings are linked to the default version.