GPT-5 Nano (batch)
OpenAI· released 7 Aug 2025
openai/gpt-5-nano:batch- Input / 1M tokens
- $0.025
- Output / 1M tokens
- $0.2
Longest answer: 128K tokens
About
GPT-5 Nano is OpenAI’s smallest and fastest variant in the GPT-5 system, described as optimized for developer tools, rapid interactions, and low-latency environments. It accepts text, images, and files and produces text. The model supports vision, tools, and reasoning. Its context window is 400,000 tokens, with a maximum output of 128,000 tokens. Batch access is indicated by the identifier openai/gpt-5-nano:batch. Pricing is $0.025 USD per 1 million input tokens and $0.2 USD per 1 million output tokens. It was released on August 7, 2025. The available description notes a trade-off: its reasoning depth is more limited than that of larger GPT-5 variants. Builders evaluating it for fast interactions can factor in that stated limitation alongside its supported inputs, context size, and token pricing.
Who it is for
It suits developers building tools or rapid interactions where latency matters. Teams considering more demanding reasoning should account for its stated limitation relative to larger variants.
What is good
- Supports text, image, and file inputs.
- Tools and vision are supported.
- 400,000-token context window.
- Input costs $0.025 USD per 1 million tokens.
- Output costs $0.2 USD per 1 million tokens.
What to know first
- Reasoning depth is more limited than larger variants.
Verdict
GPT-5 Nano offers broad input types, tool support, and a 400,000-token context window. Its listed reasoning-depth trade-off is relevant when choosing it for tasks that require deeper reasoning.
Details
- Lab
- OpenAIopenrouter.ai · 3 Oct 2026
- Context
- 400Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.025 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $0.2 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 128,000 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, image, fileopenrouter.ai · 3 Oct 2026
- Open weights
- Noopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- OpenAI Models: Pricing per 1M Tokens and Context (2026)107 listed
Sources
- openrouter.ai/openai/gpt-5-nano:batch· checked 3 Oct 2026