{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free",
  "slug": "basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free-0b4xffp",
  "url": "https://feed7.dev/p/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free-0b4xffp",
  "title": "Baseten's Mammoth-1 and Elephant-1 now available on AI Gateway for free",
  "why_included": "Baseten’s 27B and 9B decision models can classify, route, and score text with returned probabilities, giving agent workflows explicit thresholds for automation or review.",
  "summary": "Baseten’s **Mammoth-1 is 27B** and **Elephant-1 is 9B**. Both decision models accept up to **16k tokens** and return choices, probabilities, and scores for classification, routing, or criteria-based evaluation.",
  "practical_implication": "Use them where an agent needs a constrained decision rather than free-form prose. One request can ask multiple question types, while the application sets probability thresholds for automatic action versus human review.",
  "agent_context": "Baseten’s **Mammoth-1 is 27B** and **Elephant-1 is 9B**. Both decision models accept up to **16k tokens** and return choices, probabilities, and scores for classification, routing, or criteria-based evaluation.\n\nUse them where an agent needs a constrained decision rather than free-form prose. One request can ask multiple question types, while the application sets probability thresholds for automatic action versus human review.\n\nFree AI Gateway access was limited through **October 27**. The ranking claims come from two different decision indexes, so their number-one placements should not be treated as a direct head-to-head comparison.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free",
    "published_at": "2026-10-21T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "data"
  ],
  "topics": [
    "model-selection"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Free AI Gateway access was limited through **October 27**. The ranking claims come from two different decision indexes, so their number-one placements should not be treated as a direct head-to-head comparison."
  ],
  "connected_context": {
    "meaning": "This narrows model selection from general generation to constrained, probabilistic decisions suitable for routing, classification, and review gates. The 27B and 9B options create a size choice, but separate ranking indexes do not establish which is better. Applications must define thresholds and escalation policy, and the temporary free access supports evaluation rather than a durable cost assumption.",
    "corpus_size": 898,
    "generated_at": "2026-10-24T10:28:19.047Z",
    "connections": [
      {
        "title": "Jev is the fastest-adopted model in AI Gateway history",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/blog/ai-gateway-jev-model-launch",
        "feed7_url": "https://feed7.dev/p/ai-gateway-jev-model-launch-0rvbmm3",
        "reason": "Jev provides the closest architectural precedent: both return typed probabilistic decisions that can sit around general agents as routing, guardrail, or approval components."
      },
      {
        "title": "When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2608.31118v1",
        "feed7_url": "https://feed7.dev/p/2608-31118v1-1abyqwd",
        "reason": "The controlled finding that model size is a weak selector cautions against choosing Mammoth-1 over Elephant-1 from 27B versus 9B alone; task-specific decision quality still needs testing."
      },
      {
        "title": "Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are available now in AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/kimi-k3-1-pro-and-kimi-k3-1-pro-highspeed-are-available-now-in-ai-gateway",
        "feed7_url": "https://feed7.dev/p/kimi-k3-1-pro-and-kimi-k3-1-pro-highspeed-are-available-now-in-ai-gatewa-1gne8bl",
        "reason": "Kimi represents a general long-context agent model, whereas Mammoth and Elephant are specialized decision layers that could route or evaluate such models rather than replace their free-form work."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-10-21T00:00:00.000Z",
  "modified_at": "2026-10-21T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free-0b4xffp",
    "json": "https://feed7.dev/p/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free-0b4xffp.json",
    "markdown": "https://feed7.dev/p/basetens-mammoth-1-and-elephant-1-now-available-on-ai-gateway-for-free-0b4xffp.md"
  }
}