{
  "schema_version": "1.1",
  "id": "archive:https://vercel.com/changelog/deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway",
  "slug": "deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway-1hjzoii",
  "url": "https://feed7.dev/p/deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway-1hjzoii",
  "title": "DeepSeek V4.1 Flash 1017 Ultrafast now available on AI Gateway",
  "why_included": "DeepSeek V4.1 Flash 1017 Ultrafast is available through Vercel AI Gateway, with a 1M-token context and generation above 1,000 tokens per second. Builders can try it in coding agents via the Vercel CLI.",
  "summary": "Vercel AI Gateway now offers **DeepSeek V4.1 Flash 1017 Ultrafast** through Fireworks. It has a **1M-token context window** and can generate upwards of **1,000 tokens per second**; public preview has no waitroom or session time limit.",
  "practical_implication": "For interactive coding or agent workflows where waiting on each model step is a bottleneck, configure the model in Claude Code, Codex, Cursor, or another supported agent using the latest Vercel CLI.",
  "agent_context": "Vercel AI Gateway now offers **DeepSeek V4.1 Flash 1017 Ultrafast** through Fireworks. It has a **1M-token context window** and can generate upwards of **1,000 tokens per second**; public preview has no waitroom or session time limit.\n\nFor interactive coding or agent workflows where waiting on each model step is a bottleneck, configure the model in Claude Code, Codex, Cursor, or another supported agent using the latest Vercel CLI.\n\nThe material gives no task-quality or latency comparison against other models. The preview’s speed and long context do not establish how well it performs on a particular codebase.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway",
    "published_at": "2026-11-07T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "coding"
  ],
  "topics": [
    "model-selection",
    "coding-agents"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The material gives no task-quality or latency comparison against other models. The preview’s speed and long context do not establish how well it performs on a particular codebase."
  ],
  "connected_context": {
    "meaning": "This adds a Vercel-routed DeepSeek option combining a 1M-token context window with claimed throughput above 1,000 tokens per second. Nearby listings already offer million-token coding routes, and one claims similar throughput; this launch expands evaluation choices but supplies no comparative quality or latency evidence.",
    "corpus_size": 1024,
    "generated_at": "2026-11-08T11:04:46.557Z",
    "connections": [
      {
        "title": "Mercury 3 now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/mercury-3-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/mercury-3-now-available-on-ai-gateway-1iwep32",
        "reason": "Both launches claim throughput above 1,000 tokens per second and a 1M-token context for coding agents, reinforcing that these are competing evaluation options without settling which performs better."
      },
      {
        "title": "Particle-1 is now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/particle-1-is-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/particle-1-is-now-available-on-ai-gateway-0qh3hfc",
        "reason": "Both add 1M-token coding models through AI Gateway; this launch adds a specific throughput claim, while neither candidate provides comparative task results."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-11-07T00:00:00.000Z",
  "modified_at": "2026-11-07T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway-1hjzoii",
    "json": "https://feed7.dev/p/deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway-1hjzoii.json",
    "markdown": "https://feed7.dev/p/deepseek-v4-1-flash-1017-ultrafast-now-available-on-ai-gateway-1hjzoii.md"
  }
}