{
  "schema_version": "1.0",
  "id": "s4:https://vercel.com/changelog/gemini-3-6-flash-3-5-flash-lite-on-ai-gateway",
  "slug": "gemini-3-6-flash-3-5-flash-lite-on-ai-gateway-1tvu8jp",
  "url": "https://feed7.dev/p/gemini-3-6-flash-3-5-flash-lite-on-ai-gateway-1tvu8jp",
  "title": "Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway",
  "why_included": "Vercel AI Gateway added Gemini 3.6 Flash for coding and web work and Gemini 3.5 Flash-Lite for scoped subagent tasks, both available through AI SDK model IDs.",
  "summary": "**Gemini 3.6 Flash** and **Gemini 3.5 Flash-Lite** are now available through AI Gateway. Vercel says 3.6 improves coding, agentic, and web-development output while using fewer tokens and calls; 3.5 upgrades the lighter tier’s agent behavior.",
  "practical_implication": "Use **google/gemini-3.6-flash** for primary coding or web-generation trials. Consider **google/gemini-3.5-flash-lite** for narrowly scoped subagents where the lighter tier’s task fit matters more than using one model everywhere.",
  "agent_context": "**Gemini 3.6 Flash** and **Gemini 3.5 Flash-Lite** are now available through AI Gateway. Vercel says 3.6 improves coding, agentic, and web-development output while using fewer tokens and calls; 3.5 upgrades the lighter tier’s agent behavior.\n\nUse **google/gemini-3.6-flash** for primary coding or web-generation trials. Consider **google/gemini-3.5-flash-lite** for narrowly scoped subagents where the lighter tier’s task fit matters more than using one model everywhere.\n\nThe material provides no prices, latency figures, benchmark results, or direct comparison between the two models. Claims about cleaner output and lower model usage therefore need validation against your own workload.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/gemini-3-6-flash-3-5-flash-lite-on-ai-gateway",
    "published_at": "2026-07-21T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "coding"
  ],
  "topics": [
    "model-selection",
    "coding-agents",
    "subagents"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The material provides no prices, latency figures, benchmark results, or direct comparison between the two models. Claims about cleaner output and lower model usage therefore need validation against your own workload."
  ],
  "lifecycle": "Current",
  "published_at": "2026-07-21T00:00:00.000Z",
  "modified_at": "2026-07-21T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/gemini-3-6-flash-3-5-flash-lite-on-ai-gateway-1tvu8jp",
    "json": "https://feed7.dev/p/gemini-3-6-flash-3-5-flash-lite-on-ai-gateway-1tvu8jp.json",
    "markdown": "https://feed7.dev/p/gemini-3-6-flash-3-5-flash-lite-on-ai-gateway-1tvu8jp.md"
  }
}