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 Sep 8, 2026. Default version: GPT-5.4 nano
LLMBoard Score47.9GPT-5.4 nano
Coverage0%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% | Rank05 | Participants11 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents <128k | Score50.80% | Rank09 | Participants11 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkOmniDocBench 1.5 | Score75.81% | Rank13 | Participants18 | Percentile29.41% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score33.10% | Rank15 | Participants24 | Percentile39.13% | EvidenceC | Evaluated |
| BenchmarkTau2 Telecom | Score92.50% | Rank15 | Participants36 | Percentile60.00% | EvidenceC | Evaluated |
| BenchmarkFinance Agent v2 | Score38.22% | Rank17 | Participants26 | Percentile36.00% | EvidenceB | Evaluated |
| BenchmarkOSWorld-Verified | Score39.00% | Rank24 | Participants24 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLiveBench | Score70.13% | Rank30 | Participants38 | Percentile21.62% | EvidenceB | Evaluated |
| BenchmarkMCP Atlas | Score56.10% | Rank33 | Participants34 | Percentile3.03% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score35.50% | Rank37 | Participants41 | Percentile10.00% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score46.30% | Rank42 | Participants51 | Percentile18.00% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score66.10% | Rank43 | Participants69 | Percentile38.24% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score52.40% | Rank45 | Participants55 | Percentile18.52% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score24.30% | Rank60 | Participants103 | Percentile42.16% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,201.45 rating | Rank62 | Participants107 | Percentile42.45% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,197.82 rating | Rank64 | Participants107 | Percentile40.57% | EvidenceA | Evaluated |
| BenchmarkGPQA | Score82.80% | Rank78 | Participants247 | Percentile68.70% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,419.10 rating | Rank88 | Participants121 | Percentile27.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,402.21 rating | Rank106 | Participants210 | Percentile49.76% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,372.95 rating | Rank118 | Participants210 | Percentile44.02% | 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 | Rank28 | Rating / score1,388.10 | Votes421 | ObservationsN/A | Result date |
| Arenatext factuality | Categorygerman | Rank31 | Rating / score1,394.00 | Votes519 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank41 | Rating / score1,142.33 | Votes146 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank42 | Rating / score1,117.90 | Votes146 | ObservationsN/A | Result date |
| Arenatext factuality | Categorypolish | Rank47 | Rating / score1,351.68 | Votes677 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank54 | Rating / score1,235.21 | Votes1,426 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank57 | Rating / score1,442.92 | Votes1,587 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank57 | Rating / score1,231.56 | Votes1,426 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry mathematical | Rank59 | Rating / score1,431.11 | Votes2,553 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryspanish | Rank59 | Rating / score1,399.36 | Votes1,434 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank59 | Rating / score1,228.20 | Votes6,350 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank59 | Rating / score1,234.08 | Votes3,293 | ObservationsN/A | Result date |
| Arenatext factuality | Categorymath | Rank60 | Rating / score1,425.11 | Votes2,514 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank60 | Rating / score1,226.29 | Votes3,293 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank61 | Rating / score1,212.16 | Votes6,350 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank61 | Rating / score1,206.09 | Votes16,996 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank62 | Rating / score1,156.71 | Votes838 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank62 | Rating / score1,215.15 | Votes16,996 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank62 | Rating / score1,201.45 | Votes23,952 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank63 | Rating / score1,204.60 | Votes9,789 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank64 | Rating / score1,202.10 | Votes9,789 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank64 | Rating / score1,160.74 | Votes838 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank64 | Rating / score1,197.82 | Votes23,952 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank67 | Rating / score1,158.93 | Votes1,408 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank68 | Rating / score1,160.45 | Votes1,408 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexpert | Rank71 | Rating / score1,444.50 | Votes4,693 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry medicine and healthcare | Rank74 | Rating / score1,438.15 | Votes3,529 | ObservationsN/A | Result date |
| Arenatext factuality | Categorychinese | Rank76 | Rating / score1,429.13 | Votes2,560 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry legal and government | Rank76 | Rating / score1,426.49 | Votes3,671 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank78 | Rating / score1,413.33 | Votes4,922 | 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 $0.18 input, $1.1 output per 1M via Poe
- Tracked offerings
- 32
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDopenai/gpt-5.4-nano | Regionglobal | Input / 1M$0.18 | Output / 1M$1.1 | 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 |
| ProviderOpper | Provider model IDopenai/gpt-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 Zen | 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 |
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.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed118.31 tok/s | Catalog Latency3.42 s | Max Input400K | Max Output128K | Updated |
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 | LLMBoard47.89 | 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-5.1-Codex
OpenAI
OP
GPT-5
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
o4 mini
OpenAI
OP
GPT-5-Codex
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 2026-09-08.
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 $0.18 input and $1.1 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?
32 provider offerings are linked to the default version.