Skip to content

chore: remove deprecated models from the catalog #986

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Erin McNulty (erin2722) merged 4 commits into from
Jul 27, 2026
Merged

chore: remove deprecated models from the catalog #986

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3e94c8c
chore: remove models no longer served by their providers
erin2722 Jul 18, 2026
4517987
fix: don't deprecate Groq enterprise-available models
erin2722 Jul 18, 2026
447ce31
chore: remove models no longer served by their providers
erin2722 Jul 26, 2026
de26b21
Merge branch 'chore/model-deprecation-audit' of https://github.com/br…
erin2722 Jul 27, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 3 additions & 6 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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"],
Expand All @@ -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"],
Expand Down Expand Up @@ -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"],
Expand Down Expand Up @@ -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"],
Expand Down Expand Up @@ -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"],
Expand Down
47 changes: 2 additions & 45 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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",
Expand Down Expand Up @@ -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",
Expand Down Expand Up @@ -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,
Expand Down Expand Up @@ -10662,7 +10632,6 @@
"max_input_tokens": 202752,
"max_output_tokens": 128000,
"available_providers": [
"baseten",
"together"
]
},
Expand All @@ -10673,7 +10642,6 @@
"output_cost_per_mil_tokens": 3.15,
"input_cache_read_cost_per_mil_tokens": 0.2,
"available_providers": [
"baseten",
"together"
]
},
Expand Down Expand Up @@ -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",
Expand Down
3 changes: 3 additions & 0 deletions packages/proxy/scripts/deprecated_model_ids.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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",

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 18, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep enterprise-scoped Groq models routeable

When the proxy is used with Groq enterprise/committed-spend credentials, this model is still documented as available after the July 17, 2026 free/developer-tier shutdown: Groq's deprecation page says enterprise customers with a committed-spend contract are not affected, and the model card still shows a Quick Start for meta-llama/llama-4-scout-17b-16e-instruct (https://console.groq.com/docs/deprecations, https://console.groq.com/docs/model/meta-llama/llama-4-scout-17b-16e-instruct). Adding it to the sync exclusion list, together with removing it from model_list.json/AvailableEndpointTypes, makes getModelEndpointTypes(...) return no Groq route and prevents future syncs from restoring it, so those enterprise requests are incorrectly blocked instead of merely deprecated for non-enterprise use.

Useful? React with 👍 / 👎.

"mistral-large-2411",
"mistral-medium-3-5-26-04",
"mistral-saba-24b",
Expand All @@ -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",
Expand All @@ -96,6 +98,7 @@
"qwen-2.5-32b",
"qwen-2.5-coder-32b",
"qwen-qwq-32b",
"qwen/qwen3-32b",

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 18, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Do not blacklist enterprise-available Qwen on Groq

When the proxy is used with Groq enterprise/committed-spend credentials, this ID is not a definitive provider-wide removal: Groq's deprecation page scopes the July 17, 2026 shutdown to free/developer usage and says committed-spend enterprise customers are not affected, while the model card still documents qwen/qwen3-32b usage (https://console.groq.com/docs/deprecations, https://console.groq.com/docs/model/qwen/qwen3-32b). Because this addition keeps sync_models from re-adding the catalog entry and the commit also removes its Groq endpoint mapping, enterprise users who can still access the model lose routing through the proxy.

Useful? React with 👍 / 👎.

"r1-1776",
"sonar-reasoning",
"zai-org/GLM-4.6"
Expand Down
Loading