GPT-5 nano: Benchmarks, Pricing & Context Window
GPT-5 nano is a language model from OpenAI, released in August 2025, with multimodal input.
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 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GPT-5 nano across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GPT-5 nano holds up as conversations get longer.
Quality Tracker
GPT-5 nano Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Oct 20 2026GPT-5 nano pricing
Providers
GPT-5 nano starts at $0.0500 per million input tokens and $0.400 per million output tokens via OpenAI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 OpenAI | $0.0500 | — | $0.400 | 400.0K/128.0K | 0.30 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
GPT-5 nano context window
Input and output token limits for GPT-5 nano, plus how it ranks on long-context understanding.
Try now
huggleMake it with
GPT-5 nano.
GPT-5 nano latency
GPT-5 nano time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
GPT-5 nano examples
Recent arena outputs from GPT-5 nano, picked from the highest-ranked matchups.
GPT-5 nano license
GPT-5 nano is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of May 2024.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- May 2024
Proprietary license - usage restrictions apply
GPT-5 nano resources
Official sources for GPT-5 nano: provider documentation, official playground, official launch post.
GPT-5 nano vs other models
The most-compared alternatives to GPT-5 nano are Ministral 3 (14B Reasoning 2512), Qwen3.5-9B, o3. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-5 nano
Models ranked just above and below GPT-5 nano by LLM Stats score.
FAQ
Common questions about GPT-5 nano.