{
  "version": 1,
  "lastUpdated": "2026-07-22",
  "source": "https://openviglet.github.io/model-catalog",
  "vendor": "cerebras",
  "vendors": {
    "cerebras": [
      {
        "id": "gpt-oss-120b",
        "label": "GPT-OSS 120B",
        "kind": "CHAT",
        "contextWindow": 131072,
        "maxOutputTokens": 32768,
        "capabilities": [
          "tools",
          "reasoning"
        ],
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.35,
          "outputPer1M": 0.75,
          "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": 23.8,
          "scores": {
            "coding": {
              "value": 30.4
            },
            "math": {
              "value": 93.4
            }
          },
          "indicative": true,
          "note": "Cited third-party benchmark — verify at the source.",
          "source": "Artificial Analysis",
          "lastVerified": "2026-07-22"
        },
        "performance": {
          "throughputTps": 286.915,
          "latencyTtftSec": 0.506,
          "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": "cerebras"
      },
      {
        "id": "llama-3.3-70b",
        "label": "Llama 3.3 70B",
        "kind": "CHAT",
        "contextWindow": 128000,
        "maxOutputTokens": 128000,
        "capabilities": [
          "tools"
        ],
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.85,
          "outputPer1M": 1.2,
          "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": "cerebras"
      },
      {
        "id": "llama3.1-8b",
        "label": "Llama 3.1 8B",
        "kind": "CHAT",
        "contextWindow": 128000,
        "maxOutputTokens": 128000,
        "capabilities": [
          "tools"
        ],
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.1,
          "outputPer1M": 0.1,
          "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": "cerebras"
      },
      {
        "id": "qwen-3-32b",
        "label": "Qwen3 32B",
        "kind": "CHAT",
        "contextWindow": 128000,
        "maxOutputTokens": 128000,
        "capabilities": [
          "tools",
          "reasoning"
        ],
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 0.4,
          "outputPer1M": 0.8,
          "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": "cerebras"
      },
      {
        "id": "zai-glm-4.6",
        "label": "GLM-4.6",
        "kind": "CHAT",
        "contextWindow": 128000,
        "maxOutputTokens": 128000,
        "capabilities": [
          "tools",
          "reasoning"
        ],
        "modalities": {
          "input": [
            "text"
          ]
        },
        "pricing": {
          "inputPer1M": 2.25,
          "outputPer1M": 2.75,
          "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": "cerebras"
      }
    ]
  }
}