GPT-5 nano (minimal)
Intelligence
13.8
#367/521
Coding
14.2
#272/427
Math
27.3
#190/265
Speed
136 tok/s
TTFT: 707.00s
Pricing
$0.05 / $0.40
per 1M tokens (in/out)
GPT-5 nano (minimal) is OpenAI’s latest language model designed for efficient processing and coding tasks. It operates at a speed of 136.115 tokens per second and is priced at $0.05 per million input tokens, catering to developers and data professionals.
When to Use GPT-5 nano (minimal)
✓ Best For
- Rapid prototyping of code snippets.
- Data analysis and summarization tasks.
- Real-time language translation.
✗ Not Ideal For
- Complex mathematical problem-solving.
- High-volume output generation due to cost.
How GPT-5 nano (minimal) Compares
Intelligence Index · Higher is better
Allen Institute for AIxAIOpenAIGoogle
Benchmark Profile
Coding Index
AlibabaKimiOpenAIMiniMax
Output Speed · tok/s
OpenAIAmazonMistralAlibaba
Math Index
AlibabaOpenAIMistralNVIDIA
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 13.8 | |
| Coding Index | 14.2 | |
| Math Index | 27.3 | |
| MMLU-Pro | 556% | |
| GPQA | 428% | |
| LiveCodeBench | 47% | |
| HLE | 41% | |
| SciCode | 29.1% | |
| IFBench | 32.5% | |
| LCR | 20% | |
| TerminalBench Hard | 6.8% | |
| Tau2 | 25.7% | |
| AIME 2025 | 27.3% |
Data: Artificial Analysis · Updated: March 28, 2026
Frequently Asked Questions (15)
When was GPT-5 nano (minimal) released?
GPT-5 nano (minimal) was released on August 7, 2025.
Who created GPT-5 nano (minimal)?
GPT-5 nano (minimal) was created by OpenAI.
How intelligent is GPT-5 nano (minimal)?
GPT-5 nano (minimal) scores 14 on the Artificial Analysis Intelligence Index, placing it above average among other non-reasoning models in a similar price tier (median: 11).
How fast is GPT-5 nano (minimal)?
GPT-5 nano (minimal) generates output at 151.1 tokens per second (based on OpenAI's API), which is above average compared to other non-reasoning models in a similar price tier (median: 87.0 t/s).
What is the latency of GPT-5 nano (minimal)?
GPT-5 nano (minimal) has a time to first token (TTFT) of 0.97s (based on OpenAI's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 0.94s).
How much does GPT-5 nano (minimal) cost?
GPT-5 nano (minimal) costs $0.05 per 1M input tokens (very competitive, median: $0.06) and $0.40 per 1M output tokens (at the higher end, median: $0.20), based on OpenAI's API.
What is GPT-5 nano (minimal) API pricing?
GPT-5 nano (minimal) costs $0.05 per 1M input tokens and $0.40 per 1M output tokens (based on OpenAI's API). For a blended rate (3:1 input to output ratio), this is $0.14 per 1M tokens. Pricing may vary by provider.
How verbose is GPT-5 nano (minimal)?
When evaluated on the Intelligence Index, GPT-5 nano (minimal) generated 9.0M output tokens, which is at the higher end compared to other non-reasoning models in a similar price tier (median: 2.8M).
Is GPT-5 nano (minimal) a reasoning model?
No, GPT-5 nano (minimal) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does GPT-5 nano (minimal) support?
GPT-5 nano (minimal) supports text and image input.
What output modalities does GPT-5 nano (minimal) support?
GPT-5 nano (minimal) supports text output.
Can GPT-5 nano (minimal) process images?
Yes, GPT-5 nano (minimal) supports image input and can analyze, describe, and answer questions about images.
Is GPT-5 nano (minimal) multimodal?
Yes, GPT-5 nano (minimal) is multimodal. It can process text and image input and generate text output.
What is the context window of GPT-5 nano (minimal)?
GPT-5 nano (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 nano (minimal) open source?
No, GPT-5 nano (minimal) is proprietary. The model weights are not publicly available.
