GPT-5 nano (medium)
Intelligence
25.9
#201/523
Coding
22.9
#189/429
Math
78.3
#72/265
Speed
147 tok/s
TTFT: 43.47s
Pricing
$0.05 / $0.40
per 1M tokens (in/out)
GPT-5 nano (medium) is OpenAI’s advanced language model designed for efficient text processing. It operates at a speed of 146.976 tokens per second and is priced at $0.05 per million input tokens, targeting developers and businesses seeking cost-effective AI solutions.
When to Use GPT-5 nano (medium)
✓ Best For
- Text generation and summarization.
- Coding assistance and debugging.
- Mathematical problem solving.
✗ Not Ideal For
- High-volume real-time applications due to latency.
- Complex reasoning tasks where higher intelligence is required.
How GPT-5 nano (medium) Compares
Intelligence Index · Higher is better
AlibabaOpenAIGoogle
Benchmark Profile
Coding Index
LG AI ResearchAlibabaOpenAIMistralGoogle
Output Speed · tok/s
xAIAlibabaOpenAI
Math Index
MiniMaxGoogleOpenAIMBZUAI Institute of Foundation ModelsAllen Institute for AI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (13)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 25.9 | |
| Coding Index | 22.9 | |
| Math Index | 78.3 | |
| MMLU-Pro | 772% | |
| GPQA | 67% | |
| LiveCodeBench | 763% | |
| HLE | 76% | |
| SciCode | 33.8% | |
| IFBench | 65.9% | |
| LCR | 40% | |
| TerminalBench Hard | 17.4% | |
| Tau2 | 30.4% | |
| AIME 2025 | 78.3% |
Data: Artificial Analysis · Updated: March 28, 2026
Frequently Asked Questions (15)
When was GPT-5 nano (medium) released?
GPT-5 nano (medium) was released on August 7, 2025.
Who created GPT-5 nano (medium)?
GPT-5 nano (medium) was created by OpenAI.
How intelligent is GPT-5 nano (medium)?
GPT-5 nano (medium) scores 26 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 14).
How fast is GPT-5 nano (medium)?
GPT-5 nano (medium) generates output at 162.9 tokens per second (based on OpenAI's API), which is well above average compared to other reasoning models in a similar price tier (median: 123.3 t/s).
What is the latency of GPT-5 nano (medium)?
GPT-5 nano (medium) has a time to first token (TTFT) of 41.01s (based on OpenAI's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 1.00s).
How much does GPT-5 nano (medium) cost?
GPT-5 nano (medium) 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 (medium) API pricing?
GPT-5 nano (medium) 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 (medium)?
When evaluated on the Intelligence Index, GPT-5 nano (medium) generated 45M output tokens, which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 8.3M).
Is GPT-5 nano (medium) a reasoning model?
Yes, GPT-5 nano (medium) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does GPT-5 nano (medium) support?
GPT-5 nano (medium) supports text and image input.
What output modalities does GPT-5 nano (medium) support?
GPT-5 nano (medium) supports text output.
Can GPT-5 nano (medium) process images?
Yes, GPT-5 nano (medium) supports image input and can analyze, describe, and answer questions about images.
Is GPT-5 nano (medium) multimodal?
Yes, GPT-5 nano (medium) is multimodal. It can process text and image input and generate text output.
What is the context window of GPT-5 nano (medium)?
GPT-5 nano (medium) 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 (medium) open source?
No, GPT-5 nano (medium) is proprietary. The model weights are not publicly available.
