[BOT ISSUE] Groq: missing deprecation_date for llama-3.1-8b-instant, llama-3.3-70b-versatile, and qwen/qwen3-32b

[github-actions]

Summary

Three Groq-only models have been officially deprecated (as of June 17, 2026) with upcoming shutdown dates, but have no deprecation_date or deprecated flags in the catalog. These models are still active but will become dead endpoints on their shutdown dates.

Model ID	Shutdown Date	Days Remaining	Catalog Status
qwen/qwen3-32b	2026-07-17	21	Active (no deprecation flag)
llama-3.1-8b-instant	2026-08-16	51	Active (no deprecation flag)
llama-3.3-70b-versatile	2026-08-16	51	Active (no deprecation flag)

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

Sources

• Groq deprecations page — lists all three models with explicit shutdown dates (deprecated 2026-06-17)
• Groq pricing page — models still listed but marked as deprecated

Verification

Check	Status	Detail
Cross-source	✅	Deprecation confirmed on deprecations page; deprecated status confirmed on pricing page
Already fixed	✅	Confirmed no deprecation_date or deprecated flag on any of these entries
ID format	✅	All IDs match existing catalog entries
Duplicate check	✅	Not covered by #855 (which names only llama-4-maverick and kimi-k2-instruct-0905)

Verification Notes

Field	Source	Notes
deprecation_date: "2026-07-17" (qwen3-32b)	Deprecations page	Shutdown date 07/17/2026
deprecation_date: "2026-08-16" (llama-3.1-8b, llama-3.3-70b)	Same page	Shutdown date 08/16/2026
Replacement: openai/gpt-oss-120b or qwen/qwen3.6-27b	Same page	Groq-recommended replacements

Local Files Inspected

• packages/proxy/schema/model_list.json — llama-3.3-70b-versatile at line ~5457, llama-3.1-8b-instant at line ~5469, qwen/qwen3-32b at line ~3970; none have deprecation flags

{
  "kind": "stale_metadata",
  "provider": "groq",
  "models": ["llama-3.1-8b-instant", "llama-3.3-70b-versatile", "qwen/qwen3-32b"],
  "status": "active",
  "model_specs": {
    "llama-3.1-8b-instant": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.05,
      "output_cost_per_mil_tokens": 0.08,
      "displayName": "Llama 3.1 8B Instant 128k",
      "deprecation_date": "2026-08-16",
      "max_input_tokens": 131072,
      "max_output_tokens": 131072,
      "available_providers": ["groq"]
    },
    "llama-3.3-70b-versatile": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.59,
      "output_cost_per_mil_tokens": 0.79,
      "displayName": "Llama 3.3 70B Versatile 128k",
      "deprecation_date": "2026-08-16",
      "max_input_tokens": 128000,
      "max_output_tokens": 32768,
      "available_providers": ["groq"]
    },
    "qwen/qwen3-32b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.29,
      "output_cost_per_mil_tokens": 0.59,
      "displayName": "Qwen3-32B",
      "reasoning": true,
      "experimental": true,
      "deprecation_date": "2026-07-17",
      "max_input_tokens": 131072,
      "max_output_tokens": 40960,
      "available_providers": ["groq"]
    }
  },
  "source_urls": [
    "https://console.groq.com/docs/deprecations",
    "https://groq.com/pricing/"
  ]
}

[github-actions]

Prepared catalog updates for llama-3.1-8b-instant, llama-3.3-70b-versatile, qwen/qwen3-32b. Updated models: llama-3.1-8b-instant, llama-3.3-70b-versatile, qwen/qwen3-32b.

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

• llama-3.1-8b-instant: format=openai, flavor=chat, displayName=Llama 3.1 8B Instant 128k, max_input_tokens=131072, max_output_tokens=131072, pricing(input/output per 1M)=0.05/0.08, providers=groq, deprecation_date=2026-08-16
• llama-3.3-70b-versatile: format=openai, flavor=chat, displayName=Llama 3.3 70B Versatile 128k, max_input_tokens=128000, max_output_tokens=32768, pricing(input/output per 1M)=0.59/0.79, providers=groq, deprecation_date=2026-08-16
• qwen/qwen3-32b: format=openai, flavor=chat, displayName=Qwen3-32B, max_input_tokens=131072, max_output_tokens=40960, pricing(input/output per 1M)=0.29/0.59, providers=groq, reasoning=true, deprecation_date=2026-07-17

Included in the daily batch PR: #876