GPT-5 nano
Overview
Overview
GPT-5 nano is the fastest, cheapest version of GPT-5 from OpenAI. It is well-suited for summarization and classification tasks with average reasoning capabilities and very fast speed.
GPT-5 nano was released on August 7, 2025. API access is available through OpenAI.
Performance
Timeline
ReleasedUnknown
Knowledge CutoffUnknown
Specifications
Parameters
Unknown
License
Proprietary
Training Data
Unknown
Benchmarks
Benchmarks
GPT-5 nano Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Feb 19 2026Notice missing or incorrect data?Start an Issue discussion→
Pricing
Pricing
Pricing, performance, and capabilities for GPT-5 nano across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
OpenAI | $0.05 | $0.40 | 400.0K | 128.0K | 0.3 | 500.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
API Access
API Access Coming Soon
API access for GPT-5 nano will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about GPT-5 nano
GPT-5 nano was released on August 7, 2025 by OpenAI.
GPT-5 nano was created by OpenAI.
GPT-5 nano is released under the Proprietary license.
GPT-5 nano has a knowledge cutoff of May 2024. This means the model was trained on data up to this date and may not have information about events after this time.
Yes, GPT-5 nano is a multimodal model that can process both text and images as input.