{
  "object_id": "asca:openrouter-model-page-long-context-llm@2026-08-27.v1",
  "title": "Long-context LLMs for a 128K + 4K workload",
  "slug": "long-context-llm",
  "snapshot_date": "2026-08-27",
  "snapshot_time": "2026-08-27T00:23:25.942Z",
  "snapshot_time_zone": "Asia/Seoul",
  "data": {
    "raw_json": "/data/openrouter-models-2026-08-27.json",
    "normalized_csv": "/data/openrouter-models-2026-08-27.csv",
    "raw_sha256": "sha256:4faf68bfd42d825b64eb190d6ef1481ce43977cbaaa663d9f3c2e21a26b0b265",
    "csv_sha256": "sha256:6fa50aede90a6d0cfebe04d18c650728fe119bb58800b561b85414840f68c03f"
  },
  "source_urls": [
    "https://openrouter.ai/api/v1/models?sort=top-weekly"
  ],
  "scope": "Models whose listed context can fit 128,000 input plus 4,000 output tokens.",
  "formula_or_selection_rule": "Keep context >= 132,000 and positive prompt/completion prices; derived_cost_usd = 128,000 × prompt + 4,000 × completion; request price is reported separately and excluded.",
  "observed_range": {
    "rows": 275,
    "listed_models": 417
  },
  "bias": "Context metadata and price selection bias.",
  "limitation": "A listed context limit does not prove usable quality, latency, or successful long-document completion.",
  "confidence": "high",
  "rows": [
    {
      "id": "inclusionai/ling-3.0-flash",
      "name": "Ling-3.0-flash",
      "rank": 73,
      "model_id": "inclusionai/ling-3.0-flash",
      "model_name": "Ling-3.0-flash",
      "created_at": "2026-07-23T14:56:20.000Z",
      "input_price_per_token_usd": 2.1e-8,
      "output_price_per_token_usd": 6.3e-8,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.00294,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 262144,
      "supports_tools": true,
      "supports_structured_outputs": false,
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 73,
      "rank_throughput": 155,
      "rank_coding": 78,
      "rank_agentic": 66
    },
    {
      "id": "nex-agi/nex-n2-mini",
      "name": "Nex AGI: Nex-N2-Mini",
      "rank": 140,
      "model_id": "nex-agi/nex-n2-mini",
      "model_name": "Nex AGI: Nex-N2-Mini",
      "created_at": "2026-06-24T14:56:04.000Z",
      "input_price_per_token_usd": 2.5e-8,
      "output_price_per_token_usd": 1e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.0036,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 262144,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text",
        "image"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 140,
      "rank_throughput": 18,
      "rank_coding": 277,
      "rank_agentic": 268
    },
    {
      "id": "openai/gpt-5-nano:batch",
      "name": "OpenAI: GPT-5 Nano (batch)",
      "rank": 202,
      "model_id": "openai/gpt-5-nano:batch",
      "model_name": "OpenAI: GPT-5 Nano (batch)",
      "created_at": "2025-08-07T17:23:22.000Z",
      "input_price_per_token_usd": 2.5e-8,
      "output_price_per_token_usd": 2e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.004,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 400000,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text",
        "image",
        "file"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 202,
      "rank_throughput": 377,
      "rank_coding": 298,
      "rank_agentic": 296
    },
    {
      "id": "~deepseek/deepseek-v4-flash-latest",
      "name": "DeepSeek V4 Flash Latest",
      "rank": 388,
      "model_id": "~deepseek/deepseek-v4-flash-latest",
      "model_name": "DeepSeek V4 Flash Latest",
      "created_at": "2026-08-01T17:40:09.000Z",
      "input_price_per_token_usd": 3e-8,
      "output_price_per_token_usd": 7.5e-8,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.00414,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 1310720,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 388,
      "rank_throughput": 316,
      "rank_coding": 173,
      "rank_agentic": 157
    },
    {
      "id": "upstage/solar-pro4",
      "name": "Upstage: Solar Pro 4",
      "rank": 23,
      "model_id": "upstage/solar-pro4",
      "model_name": "Upstage: Solar Pro 4",
      "created_at": "2026-08-10T14:20:36.000Z",
      "input_price_per_token_usd": 3e-8,
      "output_price_per_token_usd": 1.2e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.004319999999999999,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 524288,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 23,
      "rank_throughput": 241,
      "rank_coding": 69,
      "rank_agentic": 51
    },
    {
      "id": "qwen/qwen3.7-flash",
      "name": "Qwen: Qwen3.7 Flash",
      "rank": 50,
      "model_id": "qwen/qwen3.7-flash",
      "model_name": "Qwen: Qwen3.7 Flash",
      "created_at": "2026-07-27T22:16:01.000Z",
      "input_price_per_token_usd": 3e-8,
      "output_price_per_token_usd": 1.3e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.004359999999999999,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 1000000,
      "supports_tools": true,
      "supports_structured_outputs": false,
      "input_modalities": [
        "text",
        "image",
        "video"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 50,
      "rank_throughput": 197,
      "rank_coding": 384,
      "rank_agentic": 384
    },
    {
      "id": "qwen/qwen3-30b-a3b-instruct-2507",
      "name": "Qwen: Qwen3 30B A3B Instruct 2507",
      "rank": 96,
      "model_id": "qwen/qwen3-30b-a3b-instruct-2507",
      "model_name": "Qwen: Qwen3 30B A3B Instruct 2507",
      "created_at": "2025-07-29T16:36:05.000Z",
      "input_price_per_token_usd": 4.815e-8,
      "output_price_per_token_usd": 1.9305e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.0069353999999999996,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 262144,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 96,
      "rank_throughput": 253,
      "rank_coding": 363,
      "rank_agentic": 363
    },
    {
      "id": "google/gemini-2.5-flash-lite:batch",
      "name": "Google: Gemini 2.5 Flash Lite (batch)",
      "rank": 219,
      "model_id": "google/gemini-2.5-flash-lite:batch",
      "model_name": "Google: Gemini 2.5 Flash Lite (batch)",
      "created_at": "2025-07-22T16:04:36.000Z",
      "input_price_per_token_usd": 5e-8,
      "output_price_per_token_usd": 2e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.0072,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 1048576,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text",
        "image",
        "file",
        "audio",
        "video"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 219,
      "rank_throughput": 350,
      "rank_coding": 224,
      "rank_agentic": 210
    },
    {
      "id": "nvidia/nemotron-3-nano-30b-a3b",
      "name": "NVIDIA: Nemotron 3 Nano 30B A3B",
      "rank": 177,
      "model_id": "nvidia/nemotron-3-nano-30b-a3b",
      "model_name": "NVIDIA: Nemotron 3 Nano 30B A3B",
      "created_at": "2025-12-14T16:54:35.000Z",
      "input_price_per_token_usd": 5e-8,
      "output_price_per_token_usd": 2e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.0072,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 262144,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "text"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 177,
      "rank_throughput": 70,
      "rank_coding": 148,
      "rank_agentic": 133
    },
    {
      "id": "openai/gpt-4.1-nano:batch",
      "name": "OpenAI: GPT-4.1 Nano (batch)",
      "rank": 373,
      "model_id": "openai/gpt-4.1-nano:batch",
      "model_name": "OpenAI: GPT-4.1 Nano (batch)",
      "created_at": "2025-04-14T17:22:49.000Z",
      "input_price_per_token_usd": 5e-8,
      "output_price_per_token_usd": 2e-7,
      "request_price_per_request_usd": 0,
      "derived_cost_usd": 0.0072,
      "derived_cost_basis": "$ per 128K input + 4K output text tokens",
      "context_tokens": 1047576,
      "supports_tools": true,
      "supports_structured_outputs": true,
      "input_modalities": [
        "image",
        "text",
        "file"
      ],
      "output_modalities": [
        "text"
      ],
      "rank_top_weekly": 373,
      "rank_throughput": 371,
      "rank_coding": 157,
      "rank_agentic": 147
    }
  ]
}