{
  "schema_version": "1.1",
  "id": "archive:https://vercel.com/changelog/glm-5-3-now-available-on-ai-gateway",
  "slug": "glm-5-3-now-available-on-ai-gateway-0s7o9zv",
  "url": "https://feed7.dev/p/glm-5-3-now-available-on-ai-gateway-0s7o9zv",
  "title": "GLM 5.3 now available on AI Gateway",
  "why_included": "GLM 5.3 is available through Vercel AI Gateway for coding agents, retaining a 1M-token context window while claiming better long-horizon engineering with fewer output tokens.",
  "summary": "Z.ai’s **GLM 5.3** is now on AI Gateway under zai/glm-5.3. It retains a **1M-token context window** and **128K-token maximum output**, with function calling, structured output, streaming, and context caching.",
  "practical_implication": "Builders can route Claude Code, Codex, Cursor, OpenCode, Pi, and other agents to the model through Gateway. Evaluate it on long-running repository work and security tasks, tracking output-token use against GLM 5.2 at matched effort.",
  "agent_context": "Z.ai’s **GLM 5.3** is now on AI Gateway under zai/glm-5.3. It retains a **1M-token context window** and **128K-token maximum output**, with function calling, structured output, streaming, and context caching.\n\nBuilders can route Claude Code, Codex, Cursor, OpenCode, Pi, and other agents to the model through Gateway. Evaluate it on long-running repository work and security tasks, tracking output-token use against GLM 5.2 at matched effort.\n\nThe engineering and vulnerability improvements are provider-reported, and the material gives no scores. The context and output limits are unchanged from GLM 5.2, so the release is about behavior and efficiency rather than larger capacity.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/glm-5-3-now-available-on-ai-gateway",
    "published_at": "2026-08-18T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "model",
  "domains": [
    "coding",
    "security"
  ],
  "topics": [
    "model-selection",
    "reasoning",
    "coding-agents"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The engineering and vulnerability improvements are provider-reported, and the material gives no scores. The context and output limits are unchanged from GLM 5.2, so the release is about behavior and efficiency rather than larger capacity."
  ],
  "connected_context": {
    "meaning": "GLM 5.3 adds another repository-scale and security-oriented route without expanding GLM 5.2’s capacity envelope or supplying comparative scores. Its practical value is therefore a controlled behavioral and token-efficiency trial through existing agent clients, reinforcing that context size and provider claims cannot substitute for matched workload evaluation.",
    "corpus_size": 525,
    "generated_at": "2026-08-21T10:07:37.140Z",
    "connections": [
      {
        "title": "GPT 5.6 Sol, Luna, and Terra now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/gpt-5-6-now-available-on-ai-gateway",
        "feed7_url": "https://feed7.dev/p/gpt-5-6-now-available-on-ai-gateway-106pgsr",
        "reason": "GPT 5.6’s three routing tiers provide alternative Gateway targets against which GLM 5.3 can be tested on the same coding-agent workloads."
      },
      {
        "title": "The Base Model Is Dead — Varun Singh, Arcee AI",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=xbPriQWXtWM",
        "feed7_url": "https://feed7.dev/p/the-base-model-is-dead-varun-singh-arcee-ai-02hts76",
        "reason": "The discussion of capability differences rooted in training composition explains why GLM 5.3 may behave differently despite unchanged context limits, while supporting workload trials over specification-based selection."
      },
      {
        "title": "Muse Spark 1.2 is now available on Vercel AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/muse-spark-1-2-is-now-available-on-vercel-ai-gateway",
        "feed7_url": "https://feed7.dev/p/muse-spark-1-2-is-now-available-on-vercel-ai-gateway-1h4d9nb",
        "reason": "Both releases add claimed repository-scale improvements without comparative evidence, so each has the same implementation consequence: measure failures, cost, and reliability before changing default routing."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-08-18T00:00:00.000Z",
  "modified_at": "2026-08-18T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/glm-5-3-now-available-on-ai-gateway-0s7o9zv",
    "json": "https://feed7.dev/p/glm-5-3-now-available-on-ai-gateway-0s7o9zv.json",
    "markdown": "https://feed7.dev/p/glm-5-3-now-available-on-ai-gateway-0s7o9zv.md"
  }
}