OpenAI: GPT-5 Nano

Description

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 counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.

Raw fields snapshot

{
  "id": "openai/gpt-5-nano",
  "name": "OpenAI: GPT-5 Nano",
  "description": "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 counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.",
  "created": 1754587402,
  "canonical_slug": "openai/gpt-5-nano-2025-08-07",
  "hugging_face_id": "",
  "source_type": "both",
  "context_length": 400000,
  "max_completion_tokens": 128000,
  "is_moderated": true,
  "architecture": {
    "modality": "text+image+file->text",
    "input_modalities": [
      "text",
      "image",
      "file"
    ],
    "output_modalities": [
      "text"
    ],
    "tokenizer": "GPT",
    "instruct_type": null
  },
  "input_modalities": [
    "text",
    "image",
    "file"
  ],
  "output_modalities": [
    "text"
  ],
  "modality": "text+image+file->text",
  "tokenizer": "GPT",
  "instruct_type": null,
  "supported_parameters": [
    "include_reasoning",
    "max_tokens",
    "reasoning",
    "response_format",
    "seed",
    "structured_outputs",
    "tool_choice",
    "tools"
  ],
  "default_parameters": {},
  "per_request_limits": null,
  "top_provider": {
    "context_length": 400000,
    "max_completion_tokens": 128000,
    "is_moderated": true
  },
  "pricing": {
    "prompt": "0.00000005",
    "completion": "0.0000004",
    "web_search": "0.01",
    "input_cache_read": "0.000000005"
  },
  "PPM": {
    "prompt": 0.05,
    "completion": 0.4,
    "web_search": 10000,
    "input_cache_read": 0.005
  },
  "openrouter_raw": {
    "id": "openai/gpt-5-nano",
    "canonical_slug": "openai/gpt-5-nano-2025-08-07",
    "hugging_face_id": "",
    "name": "OpenAI: GPT-5 Nano",
    "created": 1754587402,
    "description": "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 counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.",
    "context_length": 400000,
    "architecture": {
      "modality": "text+image+file->text",
      "input_modalities": [
        "text",
        "image",
        "file"
      ],
      "output_modalities": [
        "text"
      ],
      "tokenizer": "GPT",
      "instruct_type": null
    },
    "pricing": {
      "prompt": "0.00000005",
      "completion": "0.0000004",
      "web_search": "0.01",
      "input_cache_read": "0.000000005"
    },
    "top_provider": {
      "context_length": 400000,
      "max_completion_tokens": 128000,
      "is_moderated": true
    },
    "per_request_limits": null,
    "supported_parameters": [
      "include_reasoning",
      "max_tokens",
      "reasoning",
      "response_format",
      "seed",
      "structured_outputs",
      "tool_choice",
      "tools"
    ],
    "default_parameters": {},
    "expiration_date": null
  },
  "categories": {
    "text-expert": {
      "score": 1356,
      "rank_ub": 118,
      "votes": 317,
      "ci_95": "±34"
    },
    "text-industry-software-and-it-services": {
      "score": 1370,
      "rank_ub": 139,
      "votes": 2899,
      "ci_95": "±11"
    },
    "text-industry-writing-and-literature-and-language": {
      "score": 1291,
      "rank_ub": 174,
      "votes": 1758,
      "ci_95": "±14"
    },
    "text-overall": {
      "score": 1338,
      "rank_ub": 139,
      "votes": 8352,
      "ci_95": "±7"
    },
    "text-industry-life-and-physical-and-social-science": {
      "score": 1349,
      "rank_ub": 148,
      "votes": 1333,
      "ci_95": "±17"
    },
    "text-industry-mathematical": {
      "score": 1356,
      "rank_ub": 122,
      "votes": 439,
      "ci_95": "±29"
    },
    "text-industry-entertainment-and-sports-and-media": {
      "score": 1280,
      "rank_ub": 167,
      "votes": 1367,
      "ci_95": "±16"
    },
    "text-industry-business-and-management-and-financial-operations": {
      "score": 1333,
      "rank_ub": 137,
      "votes": 1538,
      "ci_95": "±16"
    },
    "text-industry-medicine-and-healthcare": {
      "score": 1363,
      "rank_ub": 125,
      "votes": 479,
      "ci_95": "±28"
    },
    "text-industry-legal-and-government": {
      "score": 1330,
      "rank_ub": 164,
      "votes": 487,
      "ci_95": "±27"
    },
    "text-instruction-following": {
      "score": 1325,
      "rank_ub": 134,
      "votes": 2047,
      "ci_95": "±13"
    },
    "text-math": {
      "score": 1350,
      "rank_ub": 126,
      "votes": 489,
      "ci_95": "±27"
    },
    "text-creative-writing": {
      "score": 1254,
      "rank_ub": 198,
      "votes": 920,
      "ci_95": "±20"
    },
    "text-multi-turn": {
      "score": 1326,
      "rank_ub": 146,
      "votes": 1467,
      "ci_95": "±16"
    },
    "text-hard-prompts": {
      "score": 1353,
      "rank_ub": 135,
      "votes": 3817,
      "ci_95": "±10"
    },
    "text-coding": {
      "score": 1381,
      "rank_ub": 138,
      "votes": 1689,
      "ci_95": "±15"
    },
    "text-hard-prompts-english": {
      "score": 1367,
      "rank_ub": 137,
      "votes": 1977,
      "ci_95": "±13"
    },
    "text-longer-query": {
      "score": 1328,
      "rank_ub": 155,
      "votes": 1627,
      "ci_95": "±15"
    },
    "text-english": {
      "score": 1346,
      "rank_ub": 154,
      "votes": 4054,
      "ci_95": "±9"
    },
    "text-chinese": {
      "score": 1378,
      "rank_ub": 109,
      "votes": 384,
      "ci_95": "±30"
    },
    "text-spanish": {
      "score": 1387,
      "rank_ub": 69,
      "votes": 208,
      "ci_95": "±43"
    },
    "text-russian": {
      "score": 1313,
      "rank_ub": 148,
      "votes": 493,
      "ci_95": "±26"
    },
    "text-german": {
      "score": 1350,
      "rank_ub": 87,
      "votes": 204,
      "ci_95": "±41"
    },
    "text-korean": {
      "score": 1275,
      "rank_ub": 106,
      "votes": 217,
      "ci_95": "±43"
    },
    "text-exclude-ties": {
      "score": 1294,
      "rank_ub": 138,
      "votes": 6049,
      "ci_95": "±10"
    },
    "vision-overall": {
      "score": 1146,
      "rank_ub": 56,
      "votes": 4201,
      "ci_95": "±12"
    },
    "vision-english": {
      "score": 1159,
      "rank_ub": 50,
      "votes": 2098,
      "ci_95": "±15"
    },
    "vision-diagram": {
      "score": 1157,
      "rank_ub": 46,
      "votes": 531,
      "ci_95": "±27"
    },
    "vision-humor": {
      "score": 1097,
      "rank_ub": 32,
      "votes": 171,
      "ci_95": "±46"
    },
    "vision-homework": {
      "score": 1179,
      "rank_ub": 39,
      "votes": 294,
      "ci_95": "±33"
    },
    "vision-ocr": {
      "score": 1163,
      "rank_ub": 44,
      "votes": 1756,
      "ci_95": "±15"
    }
  },
  "arena_model_id": "gpt-5-nano",
  "leaderboard_name": "gpt-5-nano-high",
  "match_method": "openrouter_name",
  "match_key": "gpt-5-nano",
  "match_input": "OpenAI: GPT-5 Nano",
  "arena_aliases": []
}