{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/mercury-3-now-available-on-ai-gateway",
  "slug": "mercury-3-now-available-on-ai-gateway-1iwep32",
  "url": "https://feed7.dev/p/mercury-3-now-available-on-ai-gateway-1iwep32",
  "title": "Mercury 3 now available on AI Gateway",
  "why_included": "Vercel AI Gateway now exposes Mercury 3 to coding agents, pairing diffusion-based generation above 1,000 tokens per second with a 1M-token context window.",
  "summary": "Inception’s **Mercury 3** is available through Vercel AI Gateway as `inception/mercury-3`. It uses diffusion-based parallel refinement, with reported generation above **1,000 tokens per second** and a **1M-token context window**.",
  "practical_implication": "Builders can test it in Claude Code, Codex, or Cursor after installing the latest Vercel CLI and running setup. It is worth evaluating for agent loops where response latency and long working context matter.",
  "agent_context": "Inception’s **Mercury 3** is available through Vercel AI Gateway as `inception/mercury-3`. It uses diffusion-based parallel refinement, with reported generation above **1,000 tokens per second** and a **1M-token context window**.\n\nBuilders can test it in Claude Code, Codex, or Cursor after installing the latest Vercel CLI and running setup. It is worth evaluating for agent loops where response latency and long working context matter.\n\nThe speed and benchmark claims come from Inception, and the material provides no independent coding-agent comparison. The **50% launch discount** is temporary, with no end date stated.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/mercury-3-now-available-on-ai-gateway",
    "published_at": "2026-10-19T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "tools",
  "domains": [
    "coding"
  ],
  "topics": [
    "gateways",
    "coding-agents",
    "model-selection"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The speed and benchmark claims come from Inception, and the material provides no independent coding-agent comparison. The **50% launch discount** is temporary, with no end date stated."
  ],
  "connected_context": {
    "meaning": "Mercury 3 adds an unusually high claimed-throughput, million-token option for latency-sensitive agent loops, but it does not settle gateway routing. The launch discount and vendor-reported specifications make it a timely evaluation candidate, while coding quality, first-token delay, tool-loop reliability, and sustained performance over long contexts still need matched workload tests.",
    "corpus_size": 898,
    "generated_at": "2026-10-24T10:28:17.103Z",
    "connections": [
      {
        "title": "GLM 5.3 FlashX now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/glm-5-3-flashx-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/glm-5-3-flashx-now-available-on-ai-gateway-1yir9b2",
        "reason": "Mercury 3’s reported throughput above 1,000 tokens per second raises the speed-oriented comparison beyond FlashX’s roughly 200-token-per-second claim, but both still require end-to-end agent-loop testing."
      },
      {
        "title": "GLM 5.2 free for eve agents through August 27 via Blackbox on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/glm-5-2-free-for-eve-agents-through-august-27-via-blackbox-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/glm-5-2-free-for-eve-agents-through-august-27-via-blackbox-on-ai-gateway-0td7ioc",
        "reason": "Both offer a 1M-token context and temporary promotional pricing, reinforcing that capacity and discounted access create evaluation opportunities rather than evidence for permanent routing changes."
      },
      {
        "title": "GPT-6 Sol and Luna now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/gpt-6-sol-and-luna-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/gpt-6-sol-and-luna-now-available-on-ai-gateway-11bfugh",
        "reason": "Mercury 3 adds another candidate to the same workload-tiering decision: claimed generation speed may suit volume-sensitive loops, while demanding coding quality remains an untested comparison."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-10-19T00:00:00.000Z",
  "modified_at": "2026-10-19T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/mercury-3-now-available-on-ai-gateway-1iwep32",
    "json": "https://feed7.dev/p/mercury-3-now-available-on-ai-gateway-1iwep32.json",
    "markdown": "https://feed7.dev/p/mercury-3-now-available-on-ai-gateway-1iwep32.md"
  }
}