OpenAI model product
GPT-4.1
1 is an OpenAI large language model described as its latest flagship model.
Updated Sep 8, 2026. Default version: GPT-4.1
LLMBoard Score30.7GPT-4.1
Coverage80%28 benchmark families
Context window1MTokens
Official input price$2OpenAI API
GPT-4.1 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-4.1 Benchmark Results
Benchmark scores for GPT-4.1.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkVideo-MME (long, no subtitles) | Score72.00% | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkComplexFuncBench | Score65.50% | Rank02 | Participants7 | Percentile83.33% | EvidenceC | Evaluated |
| BenchmarkOpenAI-MRCR: 2 needle 1M | Score46.30% | Rank03 | Participants5 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkInternal API instruction following (hard) | Score49.10% | Rank04 | Participants7 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkOpenAI-MRCR: 2 needle 128k | Score57.20% | Rank04 | Participants9 | Percentile62.50% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents >128k | Score25.00% | Rank05 | Participants7 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot Edit | Score52.90% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkCOLLIE | Score65.80% | Rank06 | Participants10 | Percentile44.44% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS <128k | Score61.70% | Rank07 | Participants11 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkCharXiv-D | Score87.90% | Rank08 | Participants17 | Percentile56.25% | EvidenceC | Evaluated |
| BenchmarkGraphwalks parents <128k | Score58.00% | Rank08 | Participants11 | Percentile30.00% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS >128k | Score19.00% | Rank09 | Participants11 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score90.20% | Rank09 | Participants101 | Percentile92.00% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score72.20% | Rank11 | Participants39 | Percentile73.68% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score49.40% | Rank13 | Participants23 | Percentile45.45% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score68.00% | Rank14 | Participants25 | Percentile45.83% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score51.60% | Rank15 | Participants22 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score70.80% | Rank16 | Participants23 | Percentile31.82% | EvidenceC | Evaluated |
| BenchmarkMMMLU | Score87.30% | Rank20 | Participants49 | Percentile60.42% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score74.80% | Rank24 | Participants64 | Percentile63.49% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score38.30% | Rank25 | Participants29 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkHMMT 2025 | Score28.90% | Rank33 | Participants33 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score87.40% | Rank34 | Participants68 | Percentile50.75% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score56.70% | Rank46 | Participants55 | Percentile16.67% | EvidenceC | Evaluated |
| BenchmarkAIME 2024 | Score48.10% | Rank48 | Participants53 | Percentile9.62% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,214.19 rating | Rank56 | Participants107 | Percentile48.11% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,210.32 rating | Rank58 | Participants107 | Percentile46.23% | EvidenceA | Evaluated |
| BenchmarkSWE-Bench Verified | Score54.60% | Rank91 | Participants113 | Percentile19.64% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,414.41 rating | Rank94 | Participants210 | Percentile55.50% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score5.40% | Rank97 | Participants103 | Percentile5.88% | EvidenceC | Evaluated |
GPT-4.1 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 | Categorycreative writing | Rank11 | Rating / score1,233.70 | Votes1,432 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank12 | Rating / score1,208.66 | Votes428 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing | Rank15 | Rating / score1,222.90 | Votes1,432 | ObservationsN/A | Result date |
| Arenavision | Categorycaptioning | Rank19 | Rating / score1,204.47 | Votes428 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank28 | Rating / score1,208.43 | Votes391 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank29 | Rating / score1,185.41 | Votes391 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank44 | Rating / score1,216.05 | Votes1,280 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank50 | Rating / score1,247.75 | Votes1,481 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank50 | Rating / score1,249.90 | Votes1,481 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank53 | Rating / score1,235.24 | Votes1,972 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank54 | Rating / score1,210.85 | Votes1,280 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank55 | Rating / score1,226.19 | Votes11,367 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank56 | Rating / score1,181.79 | Votes1,369 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank56 | Rating / score1,214.19 | Votes41,034 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank57 | Rating / score1,194.68 | Votes1,369 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank58 | Rating / score1,226.38 | Votes1,972 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank58 | Rating / score1,210.32 | Votes41,034 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank58 | Rating / score1,231.42 | Votes2,756 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank59 | Rating / score1,214.39 | Votes2,756 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank59 | Rating / score1,217.34 | Votes11,367 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank61 | Rating / score1,207.89 | Votes19,042 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank63 | Rating / score1,428.04 | Votes3,049 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank63 | Rating / score1,209.29 | Votes19,042 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank72 | Rating / score1,402.50 | Votes6,589 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry entertainment and sports and media | Rank73 | Rating / score1,400.68 | Votes8,922 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank73 | Rating / score1,370.24 | Votes1,040 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank75 | Rating / score1,437.04 | Votes3,219 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank79 | Rating / score1,404.83 | Votes11,225 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank79 | Rating / score1,430.85 | Votes8,705 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank80 | Rating / score1,409.45 | Votes1,278 | ObservationsN/A | Result date |
GPT-4.1 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $2 input, $8 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $1.8 input, $7.2 output per 1M via Poe
- Tracked offerings
- 16
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$1.8 | Output / 1M$7.2 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderOpenAI | Provider model IDgpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderLLM Gateway | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderFastRouter | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderOfox | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-4.1 | Regionglobal | Input / 1M$2 | Output / 1M$8 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-4.1 Runtime Performance
Provider-specific output speed and catalog latency for GPT-4.1. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed100.00 tok/s | Catalog Latency10.00 s | Max Input1M | Max Output32.8K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-4.1 Specifications
Technical details for the model's default version.
- Version
- GPT-4.1
- Released
- Apr 14, 2025
- Knowledge cutoff
- Jun 1, 2024
- Parameters
- N/A
- Context window
- 1M
- Max output
- 32.8K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-4.1 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-4.1 | Released | LLMBoard30.74 | ParametersN/A | Context1M | Max output32.8K | Open weightsNo | LicenseProprietary |
Models similar to GPT-4.1
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5-Nano
OpenAI
OP
o1 pro
OpenAI
OP
o3 mini
OpenAI
OP
GPT-4.5
OpenAI
OP
o1
OpenAI
OP
GPT-4.1-mini
OpenAI
What is GPT-4.1?
Key information about GPT-4.1 and its available data.
1 is an LLM from OpenAI. It is described as improving on GPT-4 Turbo in benchmark performance, speed, and cost-effectiveness.
Data as of 2026-09-08.
FAQ
Common questions about GPT-4.1.
When was GPT-4.1 released?
GPT-4.1's default version was released on Apr 14, 2025.
How much does GPT-4.1 cost?
GPT-4.1's official API price is $2 per million input tokens and $8 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.8 input and $7.2 output via Poe.
Who created GPT-4.1?
GPT-4.1 was created by OpenAI.
What is the context window for GPT-4.1?
The default version has a 1M token context window.
Is GPT-4.1 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-4.1?
16 provider offerings are linked to the default version.