chore: remove deprecated models from the catalog (#986)

## Model deprecation audit

Each model below returned a definitive not-found / deprecated response
from its provider (a single 404 / not-found is treated as
authoritative). Account/region-scoped providers (bedrock, vertex,
databricks) are surfaced for manual review, not auto-removed.

```json
{
  "deprecations": [
    {
      "model": "moonshotai/Kimi-K2.5",
      "provider": "baseten",
      "reason": "absent from list + probe not-found",
      "status": 410,
      "detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
    },
    {
      "model": "nvidia/Nemotron-120B-A12B",
      "provider": "baseten",
      "reason": "absent from list + probe not-found",
      "status": 410,
      "detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
    },
    {
      "model": "zai-org/GLM-5",
      "provider": "baseten",
      "reason": "absent from list + probe not-found",
      "status": 410,
      "detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
    },
    {
      "model": "zai-org/GLM-5.1",
      "provider": "baseten",
      "reason": "absent from list + probe not-found",
      "status": 410,
      "detail": "{\"error\":\"the model version you are trying to access has been deprecated.\"}\n"
    },
    {
      "model": "meta-llama/llama-4-scout-17b-16e-instruct",
      "provider": "groq",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\"error\":{\"message\":\"The model `meta-llama/llama-4-scout-17b-16e-instruct` does not exist or you do not have access to it.\",\"type\":\"invalid_request_error\",\"code"
    },
    {
      "model": "qwen/qwen3-32b",
      "provider": "groq",
      "reason": "absent from list + probe not-found",
      "status": 404,
      "detail": "{\"error\":{\"message\":\"The model `qwen/qwen3-32b` does not exist or you do not have access to it.\",\"type\":\"invalid_request_error\",\"code\":\"model_not_found\"}}\n"
    }
  ],
  "reportOnly": [
    {
      "provider": "bedrock",
      "modelCount": 122
    },
    {
      "provider": "databricks",
      "modelCount": 36
    },
    {
      "provider": "fireworks",
      "modelCount": 266
    },
    {
      "provider": "vertex",
      "modelCount": 122
    }
  ],
  "skipped": [
    {
      "provider": "cohere",
      "reason": "no adapter"
    },
    {
      "provider": "lepton",
      "reason": "no adapter"
    },
    {
      "provider": "openrouter",
      "reason": "no adapter"
    },
    {
      "provider": "replicate",
      "reason": "no adapter"
    }
  ]
}
```

---------

Co-authored-by: erin2722 <16248113+erin2722@users.noreply.github.com>
Co-authored-by: Erin McNulty <erin.mcnulty@braintrustdata.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

Author: 3 people

packages/proxy/schema/index.ts

@@ -378,7 +378,6 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
   "open-mistral-nemo-2407": ["mistral"],
   mistral: ["ollama"],
   phi: ["ollama"],
-  "meta-llama/llama-4-scout-17b-16e-instruct": ["groq"],
   "llama-3.3-70b-versatile": ["groq"],
   "llama-3.1-8b-instant": ["groq"],
   "accounts/fireworks/models/llama-guard-3-8b": ["fireworks"],
@@ -387,7 +386,6 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
   "accounts/fireworks/models/llama-guard-2-8b": ["fireworks"],
   "accounts/fireworks/models/deepseek-r1-distill-qwen-32b": ["fireworks"],
   "accounts/fireworks/models/deepseek-r1-distill-qwen-14b": ["fireworks"],
-  "qwen/qwen3-32b": ["groq"],
   "llama3-3-70b": ["lepton"],
   "llama3-2-3b": ["lepton"],
   "llama3-2-1b": ["lepton"],
@@ -687,7 +685,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
   "deepcogito/cogito-v2-1-671b": ["together"],
   "essentialai/rnj-1-instruct": ["together"],
   "Qwen/Qwen3.6-Plus": ["together"],
-  "zai-org/GLM-5.1": ["baseten", "together"],
+  "zai-org/GLM-5.1": ["together"],
   "zai-org/GLM-5.2": ["baseten", "together"],
   "MiniMaxAI/MiniMax-M2.7": ["together"],
   "MiniMaxAI/MiniMax-M3": ["together"],
@@ -757,7 +755,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
   "accounts/fireworks/models/flux-1-schnell": ["fireworks"],
   "accounts/fireworks/models/flux-kontext-max": ["fireworks"],
   "accounts/fireworks/models/flux-kontext-pro": ["fireworks"],
-  "zai-org/GLM-5": ["baseten", "together"],
+  "zai-org/GLM-5": ["together"],
   "accounts/fireworks/models/glm-4p7": ["fireworks"],
   "zai-org/GLM-4.7": ["baseten"],
   "accounts/fireworks/models/glm-4p6": ["fireworks"],
@@ -920,11 +918,10 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
   "whisper-1": ["openai", "azure"],
   "babbage-002": ["openai", "azure"],
   "davinci-002": ["openai", "azure"],
-  "nvidia/Nemotron-120B-A12B": ["baseten"],
   "fireworks_ai/WhereIsAI/UAE-Large-V1": ["fireworks"],
   "accounts/fireworks/models/kimi-k2p5": ["fireworks"],
   "accounts/fireworks/models/kimi-k2p6": ["fireworks"],
-  "moonshotai/Kimi-K2.5": ["baseten", "together"],
+  "moonshotai/Kimi-K2.5": ["together"],
   "moonshotai/Kimi-K2.6": ["baseten", "together"],
   "fireworks_ai/nomic-ai/nomic-embed-text-v1": ["fireworks"],
   "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": ["fireworks"],

packages/proxy/schema/model_list.json

@@ -6008,20 +6008,6 @@
       "groq"
     ]
   },
-  "meta-llama/llama-4-scout-17b-16e-instruct": {
-    "format": "openai",
-    "flavor": "chat",
-    "input_cost_per_mil_tokens": 0.11,
-    "output_cost_per_mil_tokens": 0.34,
-    "displayName": "Llama 4 Scout (17Bx16E)",
-    "experimental": true,
-    "deprecation_date": "2026-07-17",
-    "max_input_tokens": 131072,
-    "max_output_tokens": 8192,
-    "available_providers": [
-      "groq"
-    ]
-  },
   "llama-3.3-70b-versatile": {
     "format": "openai",
     "flavor": "chat",
@@ -6060,21 +6046,6 @@
       "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"
-    ]
-  },
   "groq/compound": {
     "format": "openai",
     "flavor": "chat",
@@ -8128,11 +8099,10 @@
     "reasoning_budget": true,
     "fallback_models": [
       "anthropic.claude-opus-5",
+      "eu.anthropic.claude-opus-5",
       "global.anthropic.claude-opus-5",
       "publishers/anthropic/models/claude-opus-5",
-      "us.anthropic.claude-opus-5",
-      "eu.anthropic.claude-opus-5",
-      "au.anthropic.claude-opus-5"
+      "us.anthropic.claude-opus-5"
     ],
     "max_input_tokens": 1000000,
     "max_output_tokens": 128000,
@@ -10662,7 +10632,6 @@
     "max_input_tokens": 202752,
     "max_output_tokens": 128000,
     "available_providers": [
-      "baseten",
       "together"
     ]
   },
@@ -10673,7 +10642,6 @@
     "output_cost_per_mil_tokens": 3.15,
     "input_cache_read_cost_per_mil_tokens": 0.2,
     "available_providers": [
-      "baseten",
       "together"
     ]
   },
@@ -10706,20 +10674,9 @@
     "output_cost_per_mil_tokens": 3,
     "input_cache_read_cost_per_mil_tokens": 0.12,
     "available_providers": [
-      "baseten",
       "together"
     ]
   },
-  "nvidia/Nemotron-120B-A12B": {
-    "format": "openai",
-    "flavor": "chat",
-    "input_cost_per_mil_tokens": 0.3,
-    "output_cost_per_mil_tokens": 0.75,
-    "input_cache_read_cost_per_mil_tokens": 0.06,
-    "available_providers": [
-      "baseten"
-    ]
-  },
   "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": {
     "format": "openai",
     "flavor": "chat",

packages/proxy/scripts/deprecated_model_ids.json

@@ -76,6 +76,7 @@
   "magistral-small-2506",
   "meta-llama/Meta-Llama-3-8B-Instruct-Turbo",
   "meta-llama/llama-4-maverick-17b-128e-instruct",
+  "meta-llama/llama-4-scout-17b-16e-instruct",
   "mistral-large-2411",
   "mistral-medium-3-5-26-04",
   "mistral-saba-24b",
@@ -85,6 +86,7 @@
   "moonshotai/Kimi-K2-Instruct-0905",
   "moonshotai/Kimi-K2-Thinking",
   "moonshotai/kimi-k2-instruct-0905",
+  "nvidia/Nemotron-120B-A12B",
   "o1-mini",
   "o1-mini-2024-09-12",
   "o1-preview",
@@ -96,6 +98,7 @@
   "qwen-2.5-32b",
   "qwen-2.5-coder-32b",
   "qwen-qwq-32b",
+  "qwen/qwen3-32b",
   "r1-1776",
   "sonar-reasoning",
   "zai-org/GLM-4.6"