OpenAI: GPT-5 Nano
The OpenAI GPT-5 Nano is a language model designed for various input modalities, including text, image, and file inputs. It can handle context lengths of up to 400,000 tokens and supports tools for further processing. The model also supports reasoning capabilities. When considering this model, factor in its pricing: $0.05 per million input tokens and $0.4 per million output tokens. While its blended benchmark score is 18.6 across one independent benchmark, it's essential to weigh these results against the cost. Those with high-input budgets or specific use cases for image and file inputs may find this model suitable for their needs.
Benchmark results
Independent, published benchmarks. Blended score 17.1 across 1 benchmark, last refreshed 2026-10-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 21.4 |
- Model ID
- openai/gpt-5-nano
- Vendor
- openai
- Released
- August 2025
- Tokenizer
- GPT
- Input Modalities
- text, image, file
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes
What it costs in practice
Computed from the current $0.05/M input and $0.40/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $1.05 |
Category rankings
Where OpenAI: GPT-5 Nano places across the 2 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #23 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #24 | Real-Time ChatLatency · of 25 ranked | 118 |
Similar models
OpenAI: GPT-6.1 Sol Pro
OpenAI: GPT-6.1 Sol Pro (batch)
OpenAI: GPT-6.1 Sol
OpenAI: GPT-6.1 Sol (batch)
OpenAI: GPT-6 Luna Pro
OpenAI: GPT-6 Luna Pro (batch)
Quick answers
- How much does OpenAI: GPT-5 Nano cost?
- $0.05 per million input tokens and $0.40 per million output tokens.
- What is OpenAI: GPT-5 Nano's context window?
- 400,000 tokens, roughly 600 pages of text in a single request.
- Does OpenAI: GPT-5 Nano support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-5 Nano process images?
- Yes, it accepts image input.