{
  "version": 1,
  "lastUpdated": "2026-07-22",
  "source": "https://openviglet.github.io/model-catalog",
  "vendor": "groq",
  "vendors": {
    "groq": [
      {
        "id": "llama-3.1-8b-instant",
        "label": "Llama 3.1 8B Instant",
        "kind": "CHAT",
        "contextWindow": 128000,
        "maxOutputTokens": 8192,
        "capabilities": [
          "tools"
        ],
        "openWeights": true,
        "parameters": 8000000000,
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.05,
          "outputPer1M": 0.08,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "llama-3.3-70b-versatile",
        "label": "Llama 3.3 70B Versatile",
        "kind": "CHAT",
        "contextWindow": 128000,
        "maxOutputTokens": 32768,
        "capabilities": [
          "tools"
        ],
        "openWeights": true,
        "parameters": 70000000000,
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.59,
          "outputPer1M": 0.79,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "meta-llama/llama-4-maverick-17b-128e-instruct",
        "label": "Llama 4 Maverick 17B",
        "kind": "CHAT",
        "contextWindow": 131072,
        "maxOutputTokens": 8192,
        "capabilities": [
          "tools",
          "vision"
        ],
        "openWeights": true,
        "parameters": 400000000000,
        "modalities": {
          "input": [
            "image",
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.2,
          "outputPer1M": 0.6,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "meta-llama/llama-4-scout-17b-16e-instruct",
        "label": "Llama 4 Scout 17B",
        "kind": "CHAT",
        "contextWindow": 131072,
        "maxOutputTokens": 8192,
        "capabilities": [
          "tools",
          "vision"
        ],
        "openWeights": true,
        "parameters": 109000000000,
        "modalities": {
          "input": [
            "image",
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.11,
          "outputPer1M": 0.34,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "moonshotai/kimi-k2-instruct-0905",
        "label": "Kimi K2 Instruct",
        "kind": "CHAT",
        "contextWindow": 262144,
        "maxOutputTokens": 16384,
        "capabilities": [
          "tools"
        ],
        "openWeights": true,
        "parameters": 1000000000000,
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 1,
          "outputPer1M": 3,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "openai/gpt-oss-120b",
        "label": "GPT-OSS 120B",
        "kind": "CHAT",
        "contextWindow": 131072,
        "maxOutputTokens": 32766,
        "capabilities": [
          "tools",
          "reasoning"
        ],
        "openWeights": true,
        "parameters": 117000000000,
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.15,
          "outputPer1M": 0.6,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "openai/gpt-oss-20b",
        "label": "GPT-OSS 20B",
        "kind": "CHAT",
        "contextWindow": 131072,
        "maxOutputTokens": 32768,
        "capabilities": [
          "tools",
          "reasoning"
        ],
        "openWeights": true,
        "parameters": 21000000000,
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.075,
          "outputPer1M": 0.3,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "benchmarks": {
          "intelligenceIndex": 14.9,
          "scores": {
            "coding": {
              "value": 20.7
            },
            "math": {
              "value": 89.3
            }
          },
          "indicative": true,
          "note": "Cited third-party benchmark — verify at the source.",
          "source": "Artificial Analysis",
          "lastVerified": "2026-07-22"
        },
        "performance": {
          "throughputTps": 243.28,
          "latencyTtftSec": 0.405,
          "indicative": true,
          "note": "Cited third-party benchmark — verify at the source.",
          "source": "Artificial Analysis",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "artificial-analysis",
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      },
      {
        "id": "qwen/qwen3-32b",
        "label": "Qwen3 32B",
        "kind": "CHAT",
        "contextWindow": 131000,
        "maxOutputTokens": 131000,
        "capabilities": [
          "tools",
          "reasoning"
        ],
        "openWeights": true,
        "parameters": 32000000000,
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.29,
          "outputPer1M": 0.59,
          "currency": "USD",
          "unit": "per_1M_tokens",
          "indicative": true,
          "note": "Indicative US list price — verify with the vendor.",
          "source": "litellm",
          "lastVerified": "2026-07-22"
        },
        "sources": [
          "committed",
          "litellm",
          "overrides"
        ],
        "lastVerified": "2026-07-22",
        "vendor": "groq"
      }
    ]
  }
}