[
  {
    "cache_read_cost": 0.075,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "arcee-trinity-large-thinking",
    "input_cost": 0.3125,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 65536,
    "name": "Trinity Large Thinking",
    "output_cost": 1.125,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-02"
  },
  {
    "cache_read_cost": 0.6,
    "cache_write_cost": 7.5,
    "context_size": 198000,
    "dialect": null,
    "id": "claude-opus-4-5",
    "input_cost": 6,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32768,
    "name": "Claude Opus 4.5",
    "output_cost": 30,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-12-06"
  },
  {
    "cache_read_cost": 0.6,
    "cache_write_cost": 7.5,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-opus-4-6",
    "input_cost": 6,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Claude Opus 4.6",
    "output_cost": 30,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-05"
  },
  {
    "cache_read_cost": 3.6,
    "cache_write_cost": 45,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-opus-4-6-fast",
    "input_cost": 36,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Claude Opus 4.6 Fast",
    "output_cost": 180,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-08"
  },
  {
    "cache_read_cost": 0.6,
    "cache_write_cost": 7.5,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-opus-4-7",
    "input_cost": 6,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Claude Opus 4.7",
    "output_cost": 30,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-16"
  },
  {
    "cache_read_cost": 3.6,
    "cache_write_cost": 45,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-opus-4-7-fast",
    "input_cost": 36,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Claude Opus 4.7 Fast",
    "output_cost": 180,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-05-14"
  },
  {
    "cache_read_cost": 0.6,
    "cache_write_cost": 7.5,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-opus-4-8",
    "input_cost": 6,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Claude Opus 4.8",
    "output_cost": 30,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-05-28"
  },
  {
    "cache_read_cost": 1.2,
    "cache_write_cost": 15,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-opus-4-8-fast",
    "input_cost": 12,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Claude Opus 4.8 Fast",
    "output_cost": 60,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-05-28"
  },
  {
    "cache_read_cost": 0.375,
    "cache_write_cost": 4.69,
    "context_size": 198000,
    "dialect": null,
    "id": "claude-sonnet-4-5",
    "input_cost": 3.75,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 64000,
    "name": "Claude Sonnet 4.5",
    "output_cost": 18.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-01-15"
  },
  {
    "cache_read_cost": 0.36,
    "cache_write_cost": 4.5,
    "context_size": 1000000,
    "dialect": null,
    "id": "claude-sonnet-4-6",
    "input_cost": 3.6,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 64000,
    "name": "Claude Sonnet 4.6",
    "output_cost": 18,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-17"
  },
  {
    "cache_read_cost": 0.16,
    "cache_write_cost": 0,
    "context_size": 160000,
    "dialect": null,
    "id": "deepseek-v3.2",
    "input_cost": 0.33,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "DeepSeek V3.2",
    "output_cost": 0.48,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-12-04"
  },
  {
    "cache_read_cost": 0.028,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "deepseek-v4-flash",
    "input_cost": 0.17,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "DeepSeek V4 Flash",
    "output_cost": 0.35,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-24"
  },
  {
    "cache_read_cost": 0.33,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "deepseek-v4-pro",
    "input_cost": 1.73,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "DeepSeek V4 Pro",
    "output_cost": 3.796,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-24"
  },
  {
    "cache_read_cost": 0.5,
    "cache_write_cost": 0.5,
    "context_size": 1000000,
    "dialect": null,
    "id": "gemini-3-1-pro-preview",
    "input_cost": 2.5,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32768,
    "name": "Gemini 3.1 Pro Preview",
    "output_cost": 15,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-19"
  },
  {
    "cache_read_cost": 0.155,
    "cache_write_cost": 0.086,
    "context_size": 1000000,
    "dialect": null,
    "id": "gemini-3-5-flash",
    "input_cost": 1.55,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Gemini 3.5 Flash",
    "output_cost": 9.45,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-05-22"
  },
  {
    "cache_read_cost": 0.07,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "gemini-3-flash-preview",
    "input_cost": 0.7,
    "input_modalities": [
      "text",
      "image",
      "pdf"
    ],
    "max_output_tokens": 65536,
    "name": "Gemini 3 Flash Preview",
    "output_cost": 3.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-12-19"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "gemma-4-uncensored",
    "input_cost": 0.1625,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 8192,
    "name": "Gemma 4 Uncensored",
    "output_cost": 0.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-04-13"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 198000,
    "dialect": null,
    "id": "google-gemma-3-27b-it",
    "input_cost": 0.12,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 16384,
    "name": "Google Gemma 3 27B Instruct",
    "output_cost": 0.2,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2025-11-04"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "google-gemma-4-26b-a4b-it",
    "input_cost": 0.1625,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 8192,
    "name": "Google Gemma 4 26B A4B Instruct",
    "output_cost": 0.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-02"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "google-gemma-4-31b-it",
    "input_cost": 0.155,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 8192,
    "name": "Google Gemma 4 31B Instruct",
    "output_cost": 0.44,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-03"
  },
  {
    "cache_read_cost": 0.23,
    "cache_write_cost": 0,
    "context_size": 2000000,
    "dialect": null,
    "id": "grok-4-20",
    "input_cost": 1.42,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "Grok 4.20",
    "output_cost": 2.83,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-12"
  },
  {
    "cache_read_cost": 0.23,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "grok-4-3",
    "input_cost": 1.42,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32000,
    "name": "Grok 4.3",
    "output_cost": 2.83,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-18"
  },
  {
    "cache_read_cost": 0.2,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "grok-build-0-1",
    "input_cost": 1,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Grok Build 0.1",
    "output_cost": 2,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-05-21"
  },
  {
    "cache_read_cost": 0.22,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "kimi-k2-5",
    "input_cost": 0.56,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Kimi K2.5",
    "output_cost": 3.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-01-27"
  },
  {
    "cache_read_cost": 0.22,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "kimi-k2-6",
    "input_cost": 0.85,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Kimi K2.6",
    "output_cost": 4.655,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-20"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "llama-3.2-3b",
    "input_cost": 0.15,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 4096,
    "name": "Llama 3.2 3B",
    "output_cost": 0.6,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2024-10-03"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "llama-3.3-70b",
    "input_cost": 0.7,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 4096,
    "name": "Llama 3.3 70B",
    "output_cost": 2.8,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2025-04-06"
  },
  {
    "cache_read_cost": 0.03125,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "mercury-2",
    "input_cost": 0.3125,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 50000,
    "name": "Mercury 2",
    "output_cost": 0.9375,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-20"
  },
  {
    "cache_read_cost": 0.04,
    "cache_write_cost": 0,
    "context_size": 198000,
    "dialect": null,
    "id": "minimax-m25",
    "input_cost": 0.34,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "MiniMax M2.5",
    "output_cost": 1.19,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-12"
  },
  {
    "cache_read_cost": 0.075,
    "cache_write_cost": 0,
    "context_size": 198000,
    "dialect": null,
    "id": "minimax-m27",
    "input_cost": 0.375,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "MiniMax M2.7",
    "output_cost": 1.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-18"
  },
  {
    "cache_read_cost": 0.06,
    "cache_write_cost": 0,
    "context_size": 500000,
    "dialect": null,
    "id": "minimax-m3",
    "input_cost": 0.3,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32768,
    "name": "MiniMax M3",
    "output_cost": 1.2,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-06-01"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "mistral-small-2603",
    "input_cost": 0.1875,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Mistral Small 4",
    "output_cost": 0.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-16"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "mistral-small-3-2-24b-instruct",
    "input_cost": 0.09375,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "Mistral Small 3.2 24B Instruct",
    "output_cost": 0.25,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-01-15"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "nvidia-nemotron-3-nano-30b-a3b",
    "input_cost": 0.075,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "NVIDIA Nemotron 3 Nano 30B",
    "output_cost": 0.3,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-01-27"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "nvidia-nemotron-cascade-2-30b-a3b",
    "input_cost": 0.14,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "Nemotron Cascade 2 30B A3B",
    "output_cost": 0.8,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-24"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 200000,
    "dialect": null,
    "id": "olafangensan-glm-4.7-flash-heretic",
    "input_cost": 0.14,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 24000,
    "name": "GLM 4.7 Flash Heretic",
    "output_cost": 0.8,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-04"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "openai-gpt-4o-2024-11-20",
    "input_cost": 3.125,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 16384,
    "name": "GPT-4o",
    "output_cost": 12.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-02-28"
  },
  {
    "cache_read_cost": 0.09375,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "openai-gpt-4o-mini-2024-07-18",
    "input_cost": 0.1875,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 16384,
    "name": "GPT-4o Mini",
    "output_cost": 0.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-02-28"
  },
  {
    "cache_read_cost": 0.219,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "openai-gpt-52",
    "input_cost": 2.19,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 65536,
    "name": "GPT-5.2",
    "output_cost": 17.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-12-13"
  },
  {
    "cache_read_cost": 0.219,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "openai-gpt-52-codex",
    "input_cost": 2.19,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "GPT-5.2 Codex",
    "output_cost": 17.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-01-15"
  },
  {
    "cache_read_cost": 0.219,
    "cache_write_cost": 0,
    "context_size": 400000,
    "dialect": null,
    "id": "openai-gpt-53-codex",
    "input_cost": 2.19,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "GPT-5.3 Codex",
    "output_cost": 17.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-24"
  },
  {
    "cache_read_cost": 0.313,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "openai-gpt-54",
    "input_cost": 3.13,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 131072,
    "name": "GPT-5.4",
    "output_cost": 18.8,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-05"
  },
  {
    "cache_read_cost": 0.09375,
    "cache_write_cost": 0,
    "context_size": 400000,
    "dialect": null,
    "id": "openai-gpt-54-mini",
    "input_cost": 0.9375,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "GPT-5.4 Mini",
    "output_cost": 5.625,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-27"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "openai-gpt-54-pro",
    "input_cost": 37.5,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "GPT-5.4 Pro",
    "output_cost": 225,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-05"
  },
  {
    "cache_read_cost": 0.625,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "openai-gpt-55",
    "input_cost": 6.25,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 131072,
    "name": "GPT-5.5",
    "output_cost": 37.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-23"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 1000000,
    "dialect": null,
    "id": "openai-gpt-55-pro",
    "input_cost": 37.5,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 128000,
    "name": "GPT-5.5 Pro",
    "output_cost": 225,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-24"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "openai-gpt-oss-120b",
    "input_cost": 0.07,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "OpenAI GPT OSS 120B",
    "output_cost": 0.3,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-11-06"
  },
  {
    "cache_read_cost": 0.0625,
    "cache_write_cost": 0.78,
    "context_size": 1000000,
    "dialect": null,
    "id": "qwen-3-6-plus",
    "input_cost": 0.625,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Qwen 3.6 Plus Uncensored",
    "output_cost": 3.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-06"
  },
  {
    "cache_read_cost": 0.27,
    "cache_write_cost": 3.35,
    "context_size": 1000000,
    "dialect": null,
    "id": "qwen-3-7-max",
    "input_cost": 2.7,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 65536,
    "name": "Qwen 3.7 Max",
    "output_cost": 8.05,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-05-22"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "qwen3-235b-a22b-instruct-2507",
    "input_cost": 0.15,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "Qwen 3 235B A22B Instruct 2507",
    "output_cost": 0.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2025-04-29"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "qwen3-235b-a22b-thinking-2507",
    "input_cost": 0.45,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "Qwen 3 235B A22B Thinking 2507",
    "output_cost": 3.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-04-29"
  },
  {
    "cache_read_cost": 0.15625,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "qwen3-5-35b-a3b",
    "input_cost": 0.3125,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 16384,
    "name": "Qwen 3.5 35B A3B",
    "output_cost": 1.25,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-25"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "qwen3-5-397b-a17b",
    "input_cost": 0.75,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32768,
    "name": "Qwen 3.5 397B",
    "output_cost": 4.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-16"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "qwen3-5-9b",
    "input_cost": 0.1,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32768,
    "name": "Qwen 3.5 9B",
    "output_cost": 0.15,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-05"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "qwen3-6-27b",
    "input_cost": 0.325,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 65536,
    "name": "Qwen 3.6 27B",
    "output_cost": 3.25,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-24"
  },
  {
    "cache_read_cost": 0.04,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "qwen3-coder-480b-a35b-instruct-turbo",
    "input_cost": 0.35,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 65536,
    "name": "Qwen 3 Coder 480B Turbo",
    "output_cost": 1.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-01-27"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "qwen3-next-80b",
    "input_cost": 0.35,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "Qwen 3 Next 80b",
    "output_cost": 1.9,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2025-04-29"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 256000,
    "dialect": null,
    "id": "qwen3-vl-235b-a22b",
    "input_cost": 0.25,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 16384,
    "name": "Qwen3 VL 235B",
    "output_cost": 1.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-01-16"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "venice-uncensored-1-2",
    "input_cost": 0.2,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 8192,
    "name": "Venice Uncensored 1.2",
    "output_cost": 0.9,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-04-01"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "venice-uncensored-role-play",
    "input_cost": 0.5,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 4096,
    "name": "Venice Role Play Uncensored",
    "output_cost": 2,
    "output_modalities": [
      "text"
    ],
    "reasoning": false,
    "release_date": "2026-02-20"
  },
  {
    "cache_read_cost": 0.24,
    "cache_write_cost": 0,
    "context_size": 200000,
    "dialect": null,
    "id": "z-ai-glm-5-turbo",
    "input_cost": 1.2,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32768,
    "name": "GLM 5 Turbo",
    "output_cost": 4,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-03-15"
  },
  {
    "cache_read_cost": 0.3,
    "cache_write_cost": 0,
    "context_size": 200000,
    "dialect": null,
    "id": "z-ai-glm-5v-turbo",
    "input_cost": 1.5,
    "input_modalities": [
      "text",
      "image"
    ],
    "max_output_tokens": 32768,
    "name": "GLM 5V Turbo",
    "output_cost": 5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-01"
  },
  {
    "cache_read_cost": 0.3,
    "cache_write_cost": 0,
    "context_size": 198000,
    "dialect": null,
    "id": "zai-org-glm-4.6",
    "input_cost": 0.85,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "GLM 4.6",
    "output_cost": 2.75,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2024-04-01"
  },
  {
    "cache_read_cost": 0.11,
    "cache_write_cost": 0,
    "context_size": 198000,
    "dialect": null,
    "id": "zai-org-glm-4.7",
    "input_cost": 0.55,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "GLM 4.7",
    "output_cost": 2.65,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2025-12-24"
  },
  {
    "cache_read_cost": 0,
    "cache_write_cost": 0,
    "context_size": 128000,
    "dialect": null,
    "id": "zai-org-glm-4.7-flash",
    "input_cost": 0.125,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 16384,
    "name": "GLM 4.7 Flash",
    "output_cost": 0.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-01-29"
  },
  {
    "cache_read_cost": 0.2,
    "cache_write_cost": 0,
    "context_size": 198000,
    "dialect": null,
    "id": "zai-org-glm-5",
    "input_cost": 1,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 32000,
    "name": "GLM 5",
    "output_cost": 3.2,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-02-11"
  },
  {
    "cache_read_cost": 0.325,
    "cache_write_cost": 0,
    "context_size": 200000,
    "dialect": null,
    "id": "zai-org-glm-5-1",
    "input_cost": 1.75,
    "input_modalities": [
      "text"
    ],
    "max_output_tokens": 24000,
    "name": "GLM 5.1",
    "output_cost": 5.5,
    "output_modalities": [
      "text"
    ],
    "reasoning": true,
    "release_date": "2026-04-07"
  }
]
