[BOT ISSUE] Groq: openai/gpt-oss-120b has stale pricing ($0.10/$0.50 → $0.15/$0.60)

[github-actions]

Summary

The openai/gpt-oss-120b entry in the catalog has pricing of $0.10/$0.50 per million tokens, but Groq's official documentation and pricing page both list $0.15/$0.60. This entry serves three providers (groq, together, baseten), so the catalog price may reflect another provider's rate, but it is incorrect for Groq.

Note: This model's cost fields are in SYNC_PRESERVED_FIELDS in sync_models.ts, meaning they are hand-maintained and won't be auto-corrected by LiteLLM sync.

Current vs Expected (Groq)

Field	Current	Expected	Source
input_cost_per_mil_tokens	0.1	0.15	Groq docs + pricing page
output_cost_per_mil_tokens	0.5	0.6	Groq docs + pricing page

Affected Entry

openai/gpt-oss-120b at line ~1313 in model_list.json:

"openai/gpt-oss-120b": {
  "format": "openai",
  "flavor": "chat",
  "input_cost_per_mil_tokens": 0.1,
  "output_cost_per_mil_tokens": 0.5,
  "input_cache_read_cost_per_mil_tokens": 0.1,
  "displayName": "OpenAI GPT-OSS (120B)",
  "reasoning": true,
  "max_input_tokens": 131072,
  "max_output_tokens": 65536,
  "available_providers": ["groq", "together", "baseten"]
}

Verification

Check	Status	Detail
Cross-source	✅	Verified from (1) Groq models page and (2) Groq pricing page — both show $0.15/$0.60
Multi-provider note	⚠️	Entry serves groq, together, and baseten — Together/Baseten pricing not independently verified. If providers differ, the entry may need to be split
Duplicate check	✅	No open issue references gpt-oss-120b pricing

Verification Notes

Field	Source	Notes
$0.15/M input	Groq models page	Listed alongside model specs
$0.60/M output	Groq pricing page	Confirmed on separate pricing page

Local Files Inspected

• packages/proxy/schema/model_list.json — openai/gpt-oss-120b at line ~1313
• packages/proxy/scripts/sync_models.ts — openai/gpt-oss costs listed in SYNC_PRESERVED_FIELDS

{
  "kind": "stale_metadata",
  "provider": "groq",
  "models": ["openai/gpt-oss-120b"],
  "status": "active",
  "model_specs": {
    "openai/gpt-oss-120b": {
      "format": "openai",
      "flavor": "chat",
      "input_cost_per_mil_tokens": 0.15,
      "output_cost_per_mil_tokens": 0.6,
      "input_cache_read_cost_per_mil_tokens": 0.1,
      "displayName": "OpenAI GPT-OSS (120B)",
      "reasoning": true,
      "max_input_tokens": 131072,
      "max_output_tokens": 65536,
      "available_providers": ["groq", "together", "baseten"]
    }
  },
  "source_urls": [
    "https://console.groq.com/docs/models",
    "https://groq.com/pricing/"
  ]
}

[github-actions]

Prepared catalog updates for openai/gpt-oss-120b. Updated models: openai/gpt-oss-120b.

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

• openai/gpt-oss-120b: format=openai, flavor=chat, displayName=OpenAI GPT-OSS (120B), max_input_tokens=131072, max_output_tokens=65536, pricing(input/output per 1M)=0.15/0.6, input_cache_read_cost_per_mil_tokens=0.1, providers=groq|together|baseten, reasoning=true

Included in the daily batch PR: #926