OpenAI: gpt-5-nano-2025-08-07:free
gpt-5-nano-2025-08-07:free
400K context128K outReasoningToolsParallel toolsVisionFilesCacheStructuredStreamingSystem msg
Released Aug 7, 2025Knowledge cutoff 2024Updated Aug 7, 2025
The most lightweight version in the GPT-5 family, released in August 2025. Designed to provide instant responses with minimal computational overhead, it is optimized for simple instruction following, high-throughput classification, real-time summarization, and mobile/edge deployments. While less powerful in complex reasoning, it offers dominant performance for handling thousands of concurrent requests.
Mode chatTokenizer GPT
Pricing
Input price
$0.00/ 1M tokens
Output price
$0.00/ 1M tokens
Context window 400K tokensCompatible endpoints openaiVendor OpenAI
Performance
Loading performance data...
Usage & Ranking
Loading usage...
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | Some providers | Not sent by default |
| include_reasoning | All providers | - |
| max_completion_tokens | Some providers | - |
| max_tokens | Some providers | - |
| presence_penalty | Some providers | Not sent by default |
| reasoning | All providers | - |
| repetition_penalty | Some providers | Not sent by default |
| response_format | All providers | - |
| seed | All providers | - |
| structured_outputs | All providers | - |
| temperature | Some providers | Not sent by default |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | Some providers | Not sent by default |
| top_p | Some providers | Not sent by default |