[BOT ISSUE] Groq: missing deprecation flags for deepseek-r1-distill-llama-70b-specdec, deepseek-r1-distill-qwen-32b, and qwen-2.5-32b

[github-actions]

Summary

Three Groq-only models are past their official shutdown dates but have no deprecated flag in the catalog. These are dead endpoints.

Model ID	Shutdown Date	Days Since Shutdown
deepseek-r1-distill-llama-70b-specdec	2025-04-14	439
deepseek-r1-distill-qwen-32b	2025-04-14	439
qwen-2.5-32b	2025-04-14	439

All three have available_providers: ["groq"] — Groq is their only provider.

Sources

• Groq deprecations page — lists all three with shutdown date 04/14/2025
• Groq pricing page — none of these models are listed (confirming shutdown)

Verification

Check	Status	Detail
Cross-source	✅	Shutdown dates confirmed on deprecations page; absence confirmed on pricing page
Already fixed	✅	Confirmed no deprecation flags on any of these entries
ID format	✅	All IDs match existing catalog entries
Duplicate check	✅	Not covered by any open issue

Local Files Inspected

• packages/proxy/schema/model_list.json — deepseek-r1-distill-llama-70b-specdec at line ~3655, deepseek-r1-distill-qwen-32b at line ~3669, qwen-2.5-32b at line ~3953

{
  "kind": "stale_metadata",
  "provider": "groq",
  "models": ["deepseek-r1-distill-llama-70b-specdec", "deepseek-r1-distill-qwen-32b", "qwen-2.5-32b"],
  "status": "active",
  "model_specs": {
    "deepseek-r1-distill-llama-70b-specdec": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.23,
      "output_cost_per_mil_tokens": 0.69,
      "displayName": "DeepSeek R1 Distill Llama 70b (Speculative Decoding)",
      "experimental": true,
      "deprecated": true,
      "deprecation_date": "2025-04-14",
      "available_providers": ["groq"]
    },
    "deepseek-r1-distill-qwen-32b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.23,
      "output_cost_per_mil_tokens": 0.69,
      "displayName": "DeepSeek R1 Distill Qwen 32b",
      "experimental": true,
      "deprecated": true,
      "deprecation_date": "2025-04-14",
      "available_providers": ["groq"]
    },
    "qwen-2.5-32b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.29,
      "output_cost_per_mil_tokens": 0.39,
      "displayName": "Qwen 2.5 32B",
      "deprecated": true,
      "deprecation_date": "2025-04-14",
      "available_providers": ["groq"]
    }
  },
  "source_urls": [
    "https://console.groq.com/docs/deprecations",
    "https://groq.com/pricing/"
  ]
}

[github-actions]

Prepared catalog updates for deepseek-r1-distill-llama-70b-specdec, deepseek-r1-distill-qwen-32b, qwen-2.5-32b. Updated models: deepseek-r1-distill-llama-70b-specdec, deepseek-r1-distill-qwen-32b, qwen-2.5-32b.

Verification sources: https://console.groq.com/docs/deprecations, https://groq.com/pricing/
Verified metadata applied:

• deepseek-r1-distill-llama-70b-specdec: format=openai, flavor=chat, displayName=DeepSeek R1 Distill Llama 70b (Speculative Decoding), max_input_tokens=not provided, max_output_tokens=not provided, pricing(input/output per 1M)=0.23/0.69, providers=groq, deprecated=true, deprecation_date=2025-04-14
• deepseek-r1-distill-qwen-32b: format=openai, flavor=chat, displayName=DeepSeek R1 Distill Qwen 32b, max_input_tokens=not provided, max_output_tokens=not provided, pricing(input/output per 1M)=0.23/0.69, providers=groq, deprecated=true, deprecation_date=2025-04-14
• qwen-2.5-32b: format=openai, flavor=chat, displayName=Qwen 2.5 32B, max_input_tokens=not provided, max_output_tokens=not provided, pricing(input/output per 1M)=0.29/0.39, providers=groq, deprecated=true, deprecation_date=2025-04-14

Included in the daily batch PR: #876