GPT-5 mini (minimal)
Intelligence
20.7
#251/523
Coding
21.9
#199/429
Math
46.7
#146/265
Speed
78 tok/s
TTFT: 977.00s
Pricing
$0.25 / $2.00
per 1M tokens (in/out)
GPT-5 mini (minimal) is OpenAI’s compact model designed for efficient processing of natural language tasks. It operates at a speed of 78.31 tokens per second and is priced at $0.25 per million input tokens, targeting professional users seeking cost-effective solutions.
When to Use GPT-5 mini (minimal)
✓ Best For
- Text generation and summarization.
- Basic coding assistance.
- Mathematical problem solving.
✗ Not Ideal For
- Highly complex coding tasks.
- Advanced mathematical computations.
How GPT-5 mini (minimal) Compares
Intelligence Index · Higher is better
OpenAIAlibabaMBZUAI Institute of Foundation ModelsGoogle
Benchmark Profile
Coding Index
ServiceNowDeepSeekOpenAIMistral
Output Speed · tok/s
OpenAIMetaNous Research
Math Index
Z AIAmazonOpenAIGoogle
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 20.7 | |
| Coding Index | 21.9 | |
| Math Index | 46.7 | |
| MMLU-Pro | 775% | |
| GPQA | 687% | |
| LiveCodeBench | 545% | |
| HLE | 5% | |
| SciCode | 36.9% | |
| IFBench | 45.6% | |
| LCR | 35.7% | |
| TerminalBench Hard | 14.4% | |
| Tau2 | 31.9% | |
| AIME 2025 | 46.7% |
Data: Artificial Analysis · Updated: March 27, 2026
Frequently Asked Questions (15)
When was GPT-5 mini (minimal) released?
GPT-5 mini (minimal) was released on August 7, 2025.
Who created GPT-5 mini (minimal)?
GPT-5 mini (minimal) was created by OpenAI.
How intelligent is GPT-5 mini (minimal)?
GPT-5 mini (minimal) scores 21 on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 15).
How fast is GPT-5 mini (minimal)?
GPT-5 mini (minimal) generates output at 73.8 tokens per second (based on OpenAI's API), which is below average compared to other non-reasoning models in a similar price tier (median: 92.9 t/s).
What is the latency of GPT-5 mini (minimal)?
GPT-5 mini (minimal) has a time to first token (TTFT) of 1.19s (based on OpenAI's API), which is better than average compared to other non-reasoning models in a similar price tier (median: 1.29s).
How much does GPT-5 mini (minimal) cost?
GPT-5 mini (minimal) costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.20) and $2.00 per 1M output tokens (at the higher end, median: $0.70), based on OpenAI's API.
What is GPT-5 mini (minimal) API pricing?
GPT-5 mini (minimal) costs $0.25 per 1M input tokens and $2.00 per 1M output tokens (based on OpenAI's API). For a blended rate (3:1 input to output ratio), this is $0.69 per 1M tokens. Pricing may vary by provider.
How verbose is GPT-5 mini (minimal)?
When evaluated on the Intelligence Index, GPT-5 mini (minimal) generated 2.9M output tokens, which is very competitive compared to other non-reasoning models in a similar price tier (median: 5.5M).
Is GPT-5 mini (minimal) a reasoning model?
No, GPT-5 mini (minimal) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does GPT-5 mini (minimal) support?
GPT-5 mini (minimal) supports text and image input.
What output modalities does GPT-5 mini (minimal) support?
GPT-5 mini (minimal) supports text output.
Can GPT-5 mini (minimal) process images?
Yes, GPT-5 mini (minimal) supports image input and can analyze, describe, and answer questions about images.
Is GPT-5 mini (minimal) multimodal?
Yes, GPT-5 mini (minimal) is multimodal. It can process text and image input and generate text output.
What is the context window of GPT-5 mini (minimal)?
GPT-5 mini (minimal) has a context window of 400k tokens. This determines how much text and conversation history the model can process in a single request.
Is GPT-5 mini (minimal) open source?
No, GPT-5 mini (minimal) is proprietary. The model weights are not publicly available.
