{
  "schema_version": "1.1",
  "id": "s4:https://vercel.com/changelog/ai-gateway-gpt-5-6-pricing-speed-updates",
  "slug": "ai-gateway-gpt-5-6-pricing-speed-updates-06cxxee",
  "url": "https://feed7.dev/p/ai-gateway-gpt-5-6-pricing-speed-updates-06cxxee",
  "title": "AI Gateway: GPT-5.6 pricing and speed updates",
  "why_included": "Vercel cut Luna and Terra token prices and raised Sol fast-mode speed without changing model IDs, so existing agent workloads inherit the changes without code edits.",
  "summary": "AI Gateway cut **GPT-5.6 Luna pricing by 80%** and **GPT-5.6 Terra pricing by 20%** across short and long contexts. Luna short-context rates are $0.20 input and $1.20 output per million tokens; Terra is $2 and $12.",
  "practical_implication": "Recheck model routing and budgets for agent workloads: Luna and Terra may now fit tasks previously assigned elsewhere. Existing requests receive the new rates because model IDs did not change.",
  "agent_context": "AI Gateway cut **GPT-5.6 Luna pricing by 80%** and **GPT-5.6 Terra pricing by 20%** across short and long contexts. Luna short-context rates are $0.20 input and $1.20 output per million tokens; Terra is $2 and $12.\n\nRecheck model routing and budgets for agent workloads: Luna and Terra may now fit tasks previously assigned elsewhere. Existing requests receive the new rates because model IDs did not change.\n\n**GPT-5.6 Sol fast mode is now 2.5x**, up from 1.5x, but its price is unchanged. The material provides only short-context dollar figures, so consult the full pricing detail before estimating long-context spend.",
  "source": {
    "name": "Vercel",
    "url": "https://vercel.com/changelog/ai-gateway-gpt-5-6-pricing-speed-updates",
    "published_at": "2026-07-30T00:00:00.000Z"
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "infra",
  "domains": [
    "coding"
  ],
  "topics": [
    "gateways",
    "model-selection"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "**GPT-5.6 Sol fast mode is now 2.5x**, up from 1.5x, but its price is unchanged. The material provides only short-context dollar figures, so consult the full pricing detail before estimating long-context spend."
  ],
  "connected_context": {
    "meaning": "This materially changes the routing economics of existing GPT-5.6 workloads without requiring model-ID migrations: Luna becomes far cheaper, Terra moderately cheaper, and Sol fast mode faster at unchanged price. It justifies rerunning task-level cost and latency evaluations, but the missing long-context figures and outcome-quality evidence prevent price changes alone from determining the new routing policy.",
    "corpus_size": 297,
    "generated_at": "2026-07-31T10:05:49.629Z",
    "connections": [
      {
        "title": "AI Gateway adds unified fast mode support",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/ai-gateway-adds-unified-fast-mode-support",
        "feed7_url": "https://feed7.dev/p/ai-gateway-adds-unified-fast-mode-support-144dq26",
        "reason": "Unified fast mode supplies the common request mechanism through which Sol’s increased fast-mode multiplier can affect existing coding-agent latency choices."
      },
      {
        "title": "Notion's Token Town — Sarah Sachs, Notion",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=-I5W5QVAT8E",
        "feed7_url": "https://feed7.dev/p/notion-s-token-town-sarah-sachs-notion-1rb6gwh",
        "reason": "The price cuts strengthen the case for revisiting routes, while Token Town cautions that per-token savings alone do not establish lower end-to-end agent cost."
      },
      {
        "title": "TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI",
        "source_name": "arXiv",
        "source_url": "https://arxiv.org/abs/2607.22465v1",
        "feed7_url": "https://feed7.dev/p/2607-22465v1-1g7nw7j",
        "reason": "TRACE-Router provides an outcome-based method for testing whether the newly cheaper Luna or Terra should own an entire task instead of routing from price alone."
      },
      {
        "title": "Routing rules now available on AI Gateway",
        "source_name": "Vercel",
        "source_url": "https://vercel.com/changelog/ai-gateway-routing-rules",
        "feed7_url": "https://feed7.dev/p/ai-gateway-routing-rules-024ifzc",
        "reason": "Routing rules make it possible to apply a reassessed Luna, Terra, or Sol policy centrally without changing application code, matching the operational consequence of the new economics."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-07-30T00:00:00.000Z",
  "modified_at": "2026-07-30T00:00:00.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/ai-gateway-gpt-5-6-pricing-speed-updates-06cxxee",
    "json": "https://feed7.dev/p/ai-gateway-gpt-5-6-pricing-speed-updates-06cxxee.json",
    "markdown": "https://feed7.dev/p/ai-gateway-gpt-5-6-pricing-speed-updates-06cxxee.md"
  }
}