{
  "schema_version": "1.0",
  "id": "s4:https://vercel.com/changelog/kimi-k3-and-kimi-k3-fast-on-ai-gateway",
  "slug": "kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6",
  "url": "https://feed7.dev/p/kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6",
  "title": "Kimi K3 and Kimi K3 Fast with ZDR and US-based providers now on AI Gateway",
  "why_included": "Kimi K3 now has US-hosted, ZDR-capable gateway routes plus a faster tier, giving coding-agent users explicit latency, residency, retention, and cost choices.",
  "summary": "AI Gateway now serves **Kimi K3 and Kimi K3 Fast** through US-based providers including Baseten and Fireworks. Both support **Zero Data Retention**, while the gateway can route across providers for fallback and capacity.",
  "practical_implication": "For coding agents, use moonshotai/kimi-k3 and select the speed option when latency matters; it falls back to standard speed if the fast tier is unavailable. Pin inferenceRegion for US-only processing, and inspect the endpoints API before choosing a provider or variant.",
  "agent_context": "AI Gateway now serves **Kimi K3 and Kimi K3 Fast** through US-based providers including Baseten and Fireworks. Both support **Zero Data Retention**, while the gateway can route across providers for fallback and capacity.\n\nFor coding agents, use moonshotai/kimi-k3 and select the speed option when latency matters; it falls back to standard speed if the fast tier is unavailable. Pin inferenceRegion for US-only processing, and inspect the endpoints API before choosing a provider or variant.\n\nKimi K3 Fast costs **about 50% more** than the base model, while US regional inference is **about 10% more** than the regular variant. Exact prices and capabilities vary by provider.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/kimi-k3-and-kimi-k3-fast-on-ai-gateway",
    "published_at": "2026-07-27T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "tools",
  "domains": [
    "coding"
  ],
  "topics": [
    "coding-agents",
    "model-selection",
    "gateways"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "Kimi K3 Fast costs **about 50% more** than the base model, while US regional inference is **about 10% more** than the regular variant. Exact prices and capabilities vary by provider."
  ],
  "lifecycle": "Current",
  "published_at": "2026-07-27T00:00:00.000Z",
  "modified_at": "2026-07-27T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6",
    "json": "https://feed7.dev/p/kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6.json",
    "markdown": "https://feed7.dev/p/kimi-k3-and-kimi-k3-fast-on-ai-gateway-0jpdaz6.md"
  }
}