OpenAI model product
o4 mini
o4-mini is OpenAI's latest small o-series model, optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.
Updated Aug 17, 2026. Default version: o4-mini
LLMBoard Score44.5o4-mini
Coverage100%14 benchmark families
Context window200KTokens
Official input price$1.1OpenAI API
o4 mini Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
o4 mini Benchmark Results
Benchmark scores for o4-mini.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAIME 2024 | Score93.4% | Rank02 | Participants53 | Percentile98.1% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot Edit | Score58.2% | Rank04 | Participants10 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score84.3% | Rank04 | Participants39 | Percentile92.1% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score68.9% | Rank07 | Participants22 | Percentile71.4% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score71.8% | Rank09 | Participants25 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score81.6% | Rank12 | Participants63 | Percentile82.3% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score49.2% | Rank14 | Participants23 | Percentile40.9% | EvidenceC | Evaluated |
| BenchmarkMulti-Challenge | Score43.0% | Rank21 | Participants29 | Percentile28.6% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score92.7% | Rank34 | Participants115 | Percentile71.0% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score72.0% | Rank35 | Participants51 | Percentile32.0% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score51.5% | Rank43 | Participants62 | Percentile31.1% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score68.1% | Rank71 | Participants111 | Percentile36.4% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score14.7% | Rank78 | Participants99 | Percentile21.4% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score81.4% | Rank83 | Participants239 | Percentile65.5% | EvidenceC | Evaluated |
o4 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 | Categoryoverall | Rank71 | Rating / score1201.6 | Votes41,833 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank76 | Rating / score1194.8 | Votes41,833 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank149 | Rating / score1369.5 | Votes2,716 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank151 | Rating / score1389.8 | Votes45,575 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank181 | Rating / score1352.4 | Votes45,575 | ObservationsN/A | Result date |
o4 mini Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.1 input, $4.4 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.99 input, $4 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/o4-mini | Regionglobal | Input / 1M$0.99 | Output / 1M$4 | Context200K | Updated |
| ProviderNanoGPT | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderImpossibl | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderJiekou.AI | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderOpenRouter | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderOpenAI | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderHelicone | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderAzure Cognitive Services | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderAzure | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderEden AI | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderLLM Gateway | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/o4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
| ProviderAbacus | Provider model IDo4-mini | Regionglobal | Input / 1M$1.1 | Output / 1M$4.4 | Context200K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
o4 mini Runtime Performance
Provider-specific output speed and catalog latency for o4-mini. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed115 tok/s | Catalog Latency5.2 s | Max Input200K | Max Output100K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
o4 mini Specifications
Technical details for the model's default version.
- Version
- o4-mini
- Released
- Apr 16, 2025
- Knowledge cutoff
- May 31, 2024
- Parameters
- N/A
- Context window
- 200K
- Max output
- 100K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
o4 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 |
|---|
| Versiono4-mini | Released | LLMBoard44.5 | ParametersN/A | Context200K | Max output100K | Open weightsNo | LicenseProprietary |
o4 mini vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to o4 mini
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5-mini
OpenAI
OP
GPT-5-Codex
OpenAI
OP
GPT-OSS-20B
OpenAI
OP
GPT-OSS-120B
OpenAI
OP
GPT-5.4-nano
OpenAI
OP
GPT-5.3
OpenAI
What is o4 mini?
Key information about o4 mini and its available data.
o4-mini is OpenAI's latest small o-series model, optimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks. It is faster and more affordable than o3.
Data as of 2026-08-17.
FAQ
Common questions about o4 mini.
When was o4 mini released?
o4 mini's default version was released on Apr 16, 2025.
How much does o4 mini cost?
o4 mini's official API price is $1.1 per million input tokens and $4.4 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.99 input and $4 output via Poe.
Who created o4 mini?
o4 mini was created by OpenAI.
What is the context window for o4 mini?
The default version has a 200K token context window.
Is o4 mini open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer o4 mini?
19 provider offerings are linked to the default version.
What models should I compare o4 mini with?
Nearby ranked alternatives include Qwen3 VL 235B A22B Thinking, Claude Haiku 4.5, GPT-5-mini.