{
 "updated": "2026-10-12T06:04:54+00:00",
 "page": "https://shurco.ai/tools/llm-api-pricing/statistics/",
 "source": "https://openrouter.ai/api/v1/models",
 "unit": "US dollars per million tokens",
 "note": "Worked out by shurco.ai from the prices in prices.json. Free to quote with a link and the date.",
 "models": 338,
 "paid_models": 338,
 "free_models": 0,
 "providers": 49,
 "median_input": 0.45,
 "median_output": 1.6,
 "median_output_to_input_ratio": 4.0,
 "cheapest_paid_model": {
  "id": "meta-llama/llama-3.1-8b-instruct",
  "name": "Llama 3.1 8B Instruct",
  "provider": "Meta",
  "input": 0.02,
  "output": 0.04
 },
 "most_expensive_model": {
  "id": "openai/o1-pro",
  "name": "o1-pro",
  "provider": "OpenAI",
  "input": 150.0,
  "output": 600.0
 },
 "paid_models_under_1_dollar_input": 221,
 "models_with_batch_price": 76,
 "models_with_cached_input_price": 214,
 "median_cached_input_discount": 0.897,
 "largest_context": {
  "id": "x-ai/grok-4.20-multi-agent",
  "name": "Grok 4.20 Multi-Agent",
  "provider": "xAI",
  "context_tokens": 2000000
 },
 "models_with_1m_context_or_more": 107,
 "models_listed_in_last_30_days": 31,
 "input_price_bands": [
  {
   "band": "Under $0.10",
   "models": 52
  },
  {
   "band": "$0.10 to $0.49",
   "models": 120
  },
  {
   "band": "$0.50 to $0.99",
   "models": 49
  },
  {
   "band": "$1 to $2.99",
   "models": 78
  },
  {
   "band": "$3 to $9.99",
   "models": 24
  },
  {
   "band": "$10 or more",
   "models": 15
  }
 ],
 "by_provider": [
  {
   "provider": "OpenAI",
   "models": 65,
   "median_input": 2.0,
   "median_output": 10.0,
   "cheapest": {
    "id": "openai/gpt-oss-20b",
    "name": "gpt-oss-20b",
    "provider": "OpenAI",
    "input": 0.018,
    "output": 0.09
   },
   "most_expensive": {
    "id": "openai/o1-pro",
    "name": "o1-pro",
    "provider": "OpenAI",
    "input": 150.0,
    "output": 600.0
   }
  },
  {
   "provider": "Alibaba",
   "models": 42,
   "median_input": 0.1975,
   "median_output": 1.0,
   "cheapest": {
    "id": "qwen/qwen3.7-flash",
    "name": "Qwen3.7 Flash",
    "provider": "Alibaba",
    "input": 0.03,
    "output": 0.13
   },
   "most_expensive": {
    "id": "qwen/qwen3.8-max-prime",
    "name": "Qwen3.8 Max Prime",
    "provider": "Alibaba",
    "input": 4.0,
    "output": 12.0
   }
  },
  {
   "provider": "Google",
   "models": 27,
   "median_input": 0.5,
   "median_output": 3.0,
   "cheapest": {
    "id": "google/gemma-3-4b-it",
    "name": "Gemma 3 4B",
    "provider": "Google",
    "input": 0.05,
    "output": 0.1
   },
   "most_expensive": {
    "id": "google/gemini-3-pro-image",
    "name": "Nano Banana Pro (Gemini 3 Pro Image)",
    "provider": "Google",
    "input": 2.0,
    "output": 12.0
   }
  },
  {
   "provider": "Mistral",
   "models": 20,
   "median_input": 0.3255,
   "median_output": 0.75,
   "cheapest": {
    "id": "mistralai/mistral-small-24b-instruct-2501",
    "name": "Mistral Small 3",
    "provider": "Mistral",
    "input": 0.05,
    "output": 0.08
   },
   "most_expensive": {
    "id": "mistralai/mistral-medium-3-5",
    "name": "Mistral Medium 3.5",
    "provider": "Mistral",
    "input": 1.5,
    "output": 7.5
   }
  },
  {
   "provider": "Anthropic",
   "models": 16,
   "median_input": 4.5,
   "median_output": 22.5,
   "cheapest": {
    "id": "anthropic/claude-haiku-5.5",
    "name": "Claude Haiku 5.5",
    "provider": "Anthropic",
    "input": 0.1,
    "output": 0.5
   },
   "most_expensive": {
    "id": "anthropic/claude-opus-4.1",
    "name": "Claude Opus 4.1",
    "provider": "Anthropic",
    "input": 15.0,
    "output": 75.0
   }
  },
  {
   "provider": "Z.ai",
   "models": 16,
   "median_input": 0.6,
   "median_output": 2.2,
   "cheapest": {
    "id": "z-ai/glm-4.7-flash",
    "name": "GLM 4.7 Flash",
    "provider": "Z.ai",
    "input": 0.06,
    "output": 0.4
   },
   "most_expensive": {
    "id": "z-ai/glm-5.3-prime",
    "name": "GLM 5.3 Prime",
    "provider": "Z.ai",
    "input": 2.8,
    "output": 8.8
   }
  },
  {
   "provider": "DeepSeek",
   "models": 14,
   "median_input": 0.27,
   "median_output": 1.0,
   "cheapest": {
    "id": "deepseek/deepseek-v4-flash-0731",
    "name": "DeepSeek V4 Flash 0731",
    "provider": "DeepSeek",
    "input": 0.06,
    "output": 0.18
   },
   "most_expensive": {
    "id": "deepseek/deepseek-v4-pro",
    "name": "DeepSeek V4 Pro 0423",
    "provider": "DeepSeek",
    "input": 0.45,
    "output": 3.48
   }
  },
  {
   "provider": "Meta",
   "models": 14,
   "median_input": 0.14,
   "median_output": 0.325,
   "cheapest": {
    "id": "meta-llama/llama-3.1-8b-instruct",
    "name": "Llama 3.1 8B Instruct",
    "provider": "Meta",
    "input": 0.02,
    "output": 0.04
   },
   "most_expensive": {
    "id": "meta/muse-spark-1.3",
    "name": "Muse Spark 1.3",
    "provider": "Meta",
    "input": 1.25,
    "output": 4.25
   }
  },
  {
   "provider": "MiniMax",
   "models": 8,
   "median_input": 0.3,
   "median_output": 1.2,
   "cheapest": {
    "id": "minimax/minimax-01",
    "name": "MiniMax-01",
    "provider": "MiniMax",
    "input": 0.2,
    "output": 1.1
   },
   "most_expensive": {
    "id": "minimax/minimax-m1",
    "name": "MiniMax M1",
    "provider": "MiniMax",
    "input": 0.4,
    "output": 2.2
   }
  },
  {
   "provider": "Moonshot AI",
   "models": 7,
   "median_input": 0.6,
   "median_output": 2.5,
   "cheapest": {
    "id": "moonshotai/kimi-k2.5",
    "name": "Kimi K2.5",
    "provider": "Moonshot AI",
    "input": 0.5,
    "output": 2.5
   },
   "most_expensive": {
    "id": "moonshotai/kimi-k3",
    "name": "Kimi K3",
    "provider": "Moonshot AI",
    "input": 3.0,
    "output": 15.0
   }
  },
  {
   "provider": "Tencent",
   "models": 7,
   "median_input": 0.132,
   "median_output": 0.528,
   "cheapest": {
    "id": "tencent/hy-mt2-1.8b",
    "name": "Hy-MT2-1.8B",
    "provider": "Tencent",
    "input": 0.044,
    "output": 0.177
   },
   "most_expensive": {
    "id": "tencent/hy4-preview",
    "name": "Hy4 preview",
    "provider": "Tencent",
    "input": 0.834,
    "output": 2.501
   }
  },
  {
   "provider": "xAI",
   "models": 7,
   "median_input": 1.25,
   "median_output": 2.5,
   "cheapest": {
    "id": "x-ai/grok-build-0.1",
    "name": "Grok Build 0.1",
    "provider": "xAI",
    "input": 1.0,
    "output": 2.0
   },
   "most_expensive": {
    "id": "x-ai/grok-4.7",
    "name": "Grok 4.7",
    "provider": "xAI",
    "input": 2.0,
    "output": 6.0
   }
  },
  {
   "provider": "Aion Labs",
   "models": 6,
   "median_input": 0.8,
   "median_output": 1.6,
   "cheapest": {
    "id": "aion-labs/aion-3.5-mini",
    "name": "Aion 3.5 Mini",
    "provider": "Aion Labs",
    "input": 0.7,
    "output": 1.4
   },
   "most_expensive": {
    "id": "aion-labs/aion-3.5",
    "name": "Aion 3.5",
    "provider": "Aion Labs",
    "input": 3.0,
    "output": 6.0
   }
  },
  {
   "provider": "Bytedance Seed",
   "models": 6,
   "median_input": 0.25,
   "median_output": 2.0,
   "cheapest": {
    "id": "bytedance-seed/seed-1.6-flash",
    "name": "Seed 1.6 Flash",
    "provider": "Bytedance Seed",
    "input": 0.075,
    "output": 0.3
   },
   "most_expensive": {
    "id": "bytedance-seed/seed-2.0-code",
    "name": "Seed-2.0-Code",
    "provider": "Bytedance Seed",
    "input": 0.5,
    "output": 3.0
   }
  },
  {
   "provider": "Amazon",
   "models": 5,
   "median_input": 0.3,
   "median_output": 2.5,
   "cheapest": {
    "id": "amazon/nova-micro-v1",
    "name": "Nova Micro 1.0",
    "provider": "Amazon",
    "input": 0.035,
    "output": 0.14
   },
   "most_expensive": {
    "id": "amazon/nova-premier-v1",
    "name": "Nova Premier 1.0",
    "provider": "Amazon",
    "input": 2.5,
    "output": 12.5
   }
  },
  {
   "provider": "Cohere",
   "models": 5,
   "median_input": 0.3,
   "median_output": 1.5,
   "cheapest": {
    "id": "cohere/command-r7b-12-2024",
    "name": "Command R7B (12-2024)",
    "provider": "Cohere",
    "input": 0.0375,
    "output": 0.15
   },
   "most_expensive": {
    "id": "cohere/command-a",
    "name": "Command A",
    "provider": "Cohere",
    "input": 2.5,
    "output": 10.0
   }
  },
  {
   "provider": "Nvidia",
   "models": 5,
   "median_input": 0.085,
   "median_output": 0.2,
   "cheapest": {
    "id": "nvidia/nemotron-3.5-lightning",
    "name": "Nemotron 3.5 Lightning",
    "provider": "Nvidia",
    "input": 0.06,
    "output": 0.16
   },
   "most_expensive": {
    "id": "nvidia/nemotron-3-ultra-550b-a55b",
    "name": "Nemotron 3 Ultra",
    "provider": "Nvidia",
    "input": 0.5,
    "output": 2.2
   }
  },
  {
   "provider": "Perplexity",
   "models": 5,
   "median_input": 2.0,
   "median_output": 8.0,
   "cheapest": {
    "id": "perplexity/sonar",
    "name": "Sonar",
    "provider": "Perplexity",
    "input": 1.0,
    "output": 1.0
   },
   "most_expensive": {
    "id": "perplexity/sonar-pro-search",
    "name": "Sonar Pro Search",
    "provider": "Perplexity",
    "input": 3.0,
    "output": 15.0
   }
  },
  {
   "provider": "Xiaomi",
   "models": 5,
   "median_input": 0.435,
   "median_output": 0.87,
   "cheapest": {
    "id": "xiaomi/mimo-v2.6-flash",
    "name": "MiMo-V2.6-Flash",
    "provider": "Xiaomi",
    "input": 0.14,
    "output": 0.28
   },
   "most_expensive": {
    "id": "xiaomi/mimo-v2.6-pro-ultraspeed",
    "name": "MiMo-V2.6-Pro-UltraSpeed",
    "provider": "Xiaomi",
    "input": 4.35,
    "output": 8.7
   }
  },
  {
   "provider": "Inclusionai",
   "models": 4,
   "median_input": 0.0675,
   "median_output": 0.2,
   "cheapest": {
    "id": "inclusionai/ling-3.0-flash-vl",
    "name": "Ling 3.0 Flash VL",
    "provider": "Inclusionai",
    "input": 0.06,
    "output": 0.18
   },
   "most_expensive": {
    "id": "inclusionai/ling-3.0-flash-sante",
    "name": "Ling 3.0 Flash Sante",
    "provider": "Inclusionai",
    "input": 0.075,
    "output": 0.22
   }
  },
  {
   "provider": "Sakana",
   "models": 4,
   "median_input": 3.5,
   "median_output": 18.0,
   "cheapest": {
    "id": "sakana/sakana-namazu",
    "name": "Sakana Namazu",
    "provider": "Sakana",
    "input": 0.95,
    "output": 4.0
   },
   "most_expensive": {
    "id": "sakana/fugu-ultra-v2",
    "name": "Fugu Ultra v2",
    "provider": "Sakana",
    "input": 5.0,
    "output": 30.0
   }
  },
  {
   "provider": "Nousresearch",
   "models": 3,
   "median_input": 1.0,
   "median_output": 1.0,
   "cheapest": {
    "id": "nousresearch/hermes-3-llama-3.1-70b",
    "name": "Hermes 3 70B Instruct",
    "provider": "Nousresearch",
    "input": 0.7,
    "output": 0.7
   },
   "most_expensive": {
    "id": "nousresearch/hermes-4-405b",
    "name": "Hermes 4 405B",
    "provider": "Nousresearch",
    "input": 1.0,
    "output": 3.0
   }
  },
  {
   "provider": "Sao10K",
   "models": 3,
   "median_input": 0.65,
   "median_output": 0.75,
   "cheapest": {
    "id": "sao10k/l3-lunaris-8b",
    "name": "Llama 3 8B Lunaris",
    "provider": "Sao10K",
    "input": 0.04,
    "output": 0.05
   },
   "most_expensive": {
    "id": "sao10k/l3.1-euryale-70b",
    "name": "Llama 3.1 Euryale 70B v2.2",
    "provider": "Sao10K",
    "input": 0.85,
    "output": 0.85
   }
  },
  {
   "provider": "Stepfun",
   "models": 3,
   "median_input": 0.2,
   "median_output": 1.15,
   "cheapest": {
    "id": "stepfun/step-3.5-flash",
    "name": "Step 3.5 Flash",
    "provider": "Stepfun",
    "input": 0.1,
    "output": 0.3
   },
   "most_expensive": {
    "id": "stepfun/step-5-preview",
    "name": "Step 5 Preview",
    "provider": "Stepfun",
    "input": 1.0,
    "output": 2.7
   }
  },
  {
   "provider": "Thedrummer",
   "models": 3,
   "median_input": 0.4,
   "median_output": 0.5,
   "cheapest": {
    "id": "thedrummer/cydonia-24b-v4.1",
    "name": "Cydonia 24B V4.1",
    "provider": "Thedrummer",
    "input": 0.3,
    "output": 0.5
   },
   "most_expensive": {
    "id": "thedrummer/skyfall-36b-v2",
    "name": "Skyfall 36B V2",
    "provider": "Thedrummer",
    "input": 0.55,
    "output": 0.8
   }
  },
  {
   "provider": "Upstage",
   "models": 3,
   "median_input": 0.09,
   "median_output": 0.36,
   "cheapest": {
    "id": "upstage/solar-mini4",
    "name": "Solar Mini 4",
    "provider": "Upstage",
    "input": 0.05,
    "output": 0.2
   },
   "most_expensive": {
    "id": "upstage/solar-pro-3",
    "name": "Solar Pro 3",
    "provider": "Upstage",
    "input": 0.15,
    "output": 0.6
   }
  }
 ],
 "facts": [
  "On 12 October 2026, 338 AI models from 49 providers have a public API price per token.",
  "The median model costs $0.45 per million input tokens and $1.60 per million output tokens.",
  "The cheapest paid model is Llama 3.1 8B Instruct from Meta, served by DeepInfra, at $0.02 in and $0.04 out per million tokens.",
  "The most expensive is o1-pro from OpenAI, at $150.00 in and $600.00 out per million tokens.",
  "Output tokens cost 4.0 times as much as input tokens on the median model.",
  "65 percent of paid models, 221 of 338, cost under $1 per million input tokens.",
  "76 models have a cheaper batch price for jobs that can wait.",
  "Cached input is 90 percent cheaper than fresh input on the median model that offers it, and 214 models do.",
  "The largest context window is 2M tokens, on Grok 4.20 Multi-Agent. 107 models accept one million tokens or more.",
  "31 models were listed in the last 30 days."
 ]
}