GPT-5 Nano pricing & benchmarks
GPT-5 Nano is available from OpenAI at $0.050 per million input tokens and $0.400 per million output tokens ($0.138 blended at 3:1). It accepts up to 400,000 tokens of context. GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
Pricing
Per million tokens · OpenRouter
Input$0.050
Output$0.400
Blended (3:1)$0.138
Specification
openai/gpt-5-nano
Context window400K
Max output128K
ReleasedAug 2025
LicenceProprietary
Modalitiesin:text, in:image, in:file, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 69.4% ±2.8 | high effort | 2025-10-30 | Independently run · Epoch AI |
| FrontierMath T1–3 | 20.0% ±2.4 | high effort | 2026-06-12 | Independently run · Epoch AI |
| FrontierMath T4 | 2.4% ±2.4 | high effort | 2026-06-12 | Independently run · Epoch AI |
| SimpleQA Verified | 12.2% ±1.0 | high effort | 2025-12-09 | Independently run · Epoch AI |
| OTIS Mock AIME | 81.1% ±4.6 | high effort | 2025-10-31 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-120b | OpenAI | $0.070 (−49%) | 75.8% | Compare → |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−18%) | 91.0% | Compare → |
Where to run GPT-5 Nano
4 options across 2 providers · 2.2× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Uptime 24h |
|---|---|---|---|---|
| OpenAI (flex) | $0.069 | $0.025 / $0.200 | 400K | 98.2% |
| OpenAI | $0.137 | $0.050 / $0.400 | 400K | 98.2% |
| Azure | $0.137 | $0.050 / $0.400 | 400K | 100.0% |
| Azure (swedencentral) | $0.151 | $0.055 / $0.440 | 400K | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-08-08.
Compare GPT-5 Nano
FAQ
How much does GPT-5 Nano cost?
GPT-5 Nano costs $0.050 per million input tokens and $0.400 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.138 per million tokens.
What is GPT-5 Nano's context window?
GPT-5 Nano accepts up to 400,000 tokens of context, and can generate up to 128,000 output tokens.
How good is GPT-5 Nano on benchmarks?
GPT-5 Nano scores 69.4% on GPQA Diamond, independently run and published by Epoch AI. 5 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as GPT-5 Nano?
Yes — 2 models in our catalogue cost less per token than GPT-5 Nano and score at least as high on the same benchmark. The cheapest is gpt-oss-120b at $0.070 per million tokens blended.