OpenAI model product
GPT-5-Mini
GPT-5-Mini is a faster, more cost-efficient version of GPT-5 for well-defined tasks and precise prompts.
Updated Oct 23, 2026. Default version: GPT-5 mini
LLMBoard Score42.5GPT-5 mini
Coverage80%5 benchmark families
Context window400KTokens
Official input price$0.25OpenAI API
GPT-5-Mini Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5-Mini Benchmark Results
Benchmark scores for GPT-5 mini.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFrontierMath | Score22.10% | Rank12 | Participants17 | Percentile31.25% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score90.67% | Rank19 | Participants96 | Percentile81.05% | EvidenceB | EvaluatedN/A |
| BenchmarkHMMT 2025 | Score87.80% | Rank20 | Participants33 | Percentile40.63% | EvidenceC | Evaluated |
| BenchmarkAA IFBench | Score75.44% | Rank22 | Participants168 | Percentile87.43% | EvidenceB | EvaluatedN/A |
| BenchmarkAIME 2025 | Score91.10% | Rank44 | Participants122 | Percentile64.46% | EvidenceC | Evaluated |
| BenchmarkAA SciCode Subtasks | Score39.00% | Rank63 | Participants89 | Percentile29.55% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Vision | Score1,202.23 rating | Rank74 | Participants113 | Percentile34.82% | EvidenceA | Evaluated |
| BenchmarkAA LCR v1.1 | Score72.33% | Rank78 | Participants193 | Percentile59.90% | EvidenceB | EvaluatedN/A |
| BenchmarkHumanity's Last Exam | Score16.70% | Rank81 | Participants109 | Percentile25.93% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score1.43% | Rank82 | Participants200 | Percentile59.30% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Vision Style Control | Score1,184.32 rating | Rank83 | Participants113 | Percentile26.79% | EvidenceA | Evaluated |
| BenchmarkAA HLE Text No Tools | Score21.46% | Rank84 | Participants200 | Percentile58.29% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score24.97% | Rank86 | Participants201 | Percentile57.50% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score82.83% | Rank86 | Participants199 | Percentile57.07% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score82.30% | Rank90 | Participants256 | Percentile65.10% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,393.63 rating | Rank117 | Participants131 | Percentile10.77% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,373.27 rating | Rank128 | Participants218 | Percentile41.47% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,389.91 rating | Rank129 | Participants218 | Percentile41.01% | EvidenceA | Evaluated |
GPT-5-Mini Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycaptioning | Rank17 | Rating / score1,216.96 | Votes283 | ObservationsN/A | Result date |
| Arenavision style control | Categorycaptioning | Rank21 | Rating / score1,175.17 | Votes283 | ObservationsN/A | Result date |
| Arenavision style control | Categoryentity recognition | Rank21 | Rating / score1,211.19 | Votes282 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing | Rank23 | Rating / score1,181.31 | Votes1,108 | ObservationsN/A | Result date |
| Arenavision | Categoryentity recognition | Rank23 | Rating / score1,226.03 | Votes282 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank26 | Rating / score1,152.41 | Votes1,108 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank61 | Rating / score1,205.49 | Votes1,047 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank63 | Rating / score1,182.46 | Votes1,047 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank69 | Rating / score1,234.46 | Votes976 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank71 | Rating / score1,213.76 | Votes1,600 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank73 | Rating / score1,180.99 | Votes1,017 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank73 | Rating / score1,215.94 | Votes13,428 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank74 | Rating / score1,198.57 | Votes7,999 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank74 | Rating / score1,202.23 | Votes28,943 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank76 | Rating / score1,202.23 | Votes1,936 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank76 | Rating / score1,209.74 | Votes976 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank76 | Rating / score1,179.78 | Votes1,600 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank77 | Rating / score1,213.01 | Votes1,936 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank78 | Rating / score1,148.88 | Votes1,017 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank79 | Rating / score1,193.21 | Votes13,428 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank79 | Rating / score1,198.95 | Votes7,999 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank83 | Rating / score1,184.32 | Votes28,943 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank93 | Rating / score1,364.10 | Votes460 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank100 | Rating / score1,399.04 | Votes1,562 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank101 | Rating / score1,341.11 | Votes460 | ObservationsN/A | Result date |
| Arenatext factuality | Categorycoding | Rank103 | Rating / score1,458.37 | Votes863 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank106 | Rating / score1,378.11 | Votes1,562 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry life and physical and social science | Rank106 | Rating / score1,422.72 | Votes485 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank112 | Rating / score1,435.04 | Votes1,366 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank112 | Rating / score1,386.18 | Votes592 | ObservationsN/A | Result date |
GPT-5-Mini Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.25 input, $2 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.2273 input, $1.82 output per 1M via Poe
- Tracked offerings
- 19
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderPoe | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.2273 | Output / 1M$1.82 | Context400K | Updated |
| ProviderOrcaRouter | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderOpenAI | Provider model IDgpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderLLM Gateway | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context128K | Updated |
| ProviderFastRouter | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderPerplexity Agent | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderOfox | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context256K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderAI/ML API | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
| ProviderPrime Inference | Provider model IDopenai/gpt-5-mini | Regionglobal | Input / 1M$0.25 | Output / 1M$2 | Context400K | Updated |
GPT-5-Mini Runtime Performance
Provider-specific output speed and catalog latency for GPT-5 mini. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed200.00 tok/s | Catalog Latency1.00 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-Mini Specifications
Technical details for the model's default version.
- Version
- GPT-5 mini
- Released
- Aug 7, 2025
- Knowledge cutoff
- May 30, 2024
- Parameters
- N/A
- Context window
- 400K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5-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 mini | Released | LLMBoard42.47 | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to GPT-5-Mini
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-OSS-120B
OpenAI
OP
o4 mini
OpenAI
OP
GPT-5-Codex
OpenAI
OP
GPT-5.3
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
GPT-5.4-nano
OpenAI
What is GPT-5-Mini?
Key information about GPT-5-Mini and its available data.
GPT-5-Mini is an OpenAI large language model (LLM) for well-defined tasks and precise prompts, with high reasoning capabilities at reduced cost.
Data as of 2026-10-22.
FAQ
Common questions about GPT-5-Mini.
When was GPT-5-Mini released?
GPT-5-Mini's default version was released on Aug 7, 2025.
How much does GPT-5-Mini cost?
GPT-5-Mini's official API price is $0.25 per million input tokens and $2 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.2273 input and $1.82 output via Poe.
Who created GPT-5-Mini?
GPT-5-Mini was created by OpenAI.
What is the context window for GPT-5-Mini?
The default version has a 400K token context window.
Is GPT-5-Mini open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5-Mini?
19 provider offerings are linked to the default version.