From 3e94c8cd2d603693a63c688f37bea94a1c507028 Mon Sep 17 00:00:00 2001 From: erin2722 <16248113+erin2722@users.noreply.github.com> Date: Sat, 18 Jul 2026 06:58:06 +0000 Subject: [PATCH 1/3] chore: remove models no longer served by their providers --- packages/proxy/schema/index.ts | 2 -- packages/proxy/schema/model_list.json | 29 ------------------- .../proxy/scripts/deprecated_model_ids.json | 2 ++ 3 files changed, 2 insertions(+), 31 deletions(-) diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index 349a1ee9..82c5f711 100644 --- a/packages/proxy/schema/index.ts +++ b/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"], diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index 89b6c9ac..e558ffa6 100644 --- a/packages/proxy/schema/model_list.json +++ b/packages/proxy/schema/model_list.json @@ -5959,20 +5959,6 @@ "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", @@ -6011,21 +5997,6 @@ "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", diff --git a/packages/proxy/scripts/deprecated_model_ids.json b/packages/proxy/scripts/deprecated_model_ids.json index 1ccb7680..c6b1ece9 100644 --- a/packages/proxy/scripts/deprecated_model_ids.json +++ b/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", @@ -96,6 +97,7 @@ "qwen-2.5-32b", "qwen-2.5-coder-32b", "qwen-qwq-32b", + "qwen/qwen3-32b", "r1-1776", "sonar-reasoning", "zai-org/GLM-4.6" From 4517987abb7910899bb6b39aa15617e8742db194 Mon Sep 17 00:00:00 2001 From: Erin McNulty Date: Sat, 18 Jul 2026 13:36:07 +0000 Subject: [PATCH 2/3] fix: don't deprecate Groq enterprise-available models MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The audit removed meta-llama/llama-4-scout-17b-16e-instruct and qwen/qwen3-32b because they left the CI account's serverless Groq model list after Groq's 2026-07-17 free/developer-tier shutdown. But per Groq's own docs the shutdown does NOT affect enterprise/committed-spend customers, and both model cards still document usage (console.groq.com/docs/deprecations + the per-model cards) — so removing them (and blacklisting them from re-sync) blocks routing for enterprise users. Restore both to the catalog + index and drop them from deprecated_model_ids.json. Addresses the two codex P2s. Co-Authored-By: Claude Opus 4.8 --- packages/proxy/schema/index.ts | 2 ++ packages/proxy/schema/model_list.json | 29 +++++++++++++++++++ .../proxy/scripts/deprecated_model_ids.json | 2 -- 3 files changed, 31 insertions(+), 2 deletions(-) diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index 82c5f711..349a1ee9 100644 --- a/packages/proxy/schema/index.ts +++ b/packages/proxy/schema/index.ts @@ -378,6 +378,7 @@ 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"], @@ -386,6 +387,7 @@ 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"], diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index e558ffa6..89b6c9ac 100644 --- a/packages/proxy/schema/model_list.json +++ b/packages/proxy/schema/model_list.json @@ -5959,6 +5959,20 @@ "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", @@ -5997,6 +6011,21 @@ "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", diff --git a/packages/proxy/scripts/deprecated_model_ids.json b/packages/proxy/scripts/deprecated_model_ids.json index c6b1ece9..1ccb7680 100644 --- a/packages/proxy/scripts/deprecated_model_ids.json +++ b/packages/proxy/scripts/deprecated_model_ids.json @@ -76,7 +76,6 @@ "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", @@ -97,7 +96,6 @@ "qwen-2.5-32b", "qwen-2.5-coder-32b", "qwen-qwq-32b", - "qwen/qwen3-32b", "r1-1776", "sonar-reasoning", "zai-org/GLM-4.6" From 447ce31e01ce65d71212af7fcc93a74a7ae4ce45 Mon Sep 17 00:00:00 2001 From: erin2722 <16248113+erin2722@users.noreply.github.com> Date: Sun, 26 Jul 2026 07:11:48 +0000 Subject: [PATCH 3/3] chore: remove models no longer served by their providers --- packages/proxy/schema/index.ts | 9 ++-- packages/proxy/schema/model_list.json | 47 +------------------ .../proxy/scripts/deprecated_model_ids.json | 3 ++ 3 files changed, 8 insertions(+), 51 deletions(-) diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index 91eeb57a..ce14d3b6 100644 --- a/packages/proxy/schema/index.ts +++ b/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"], diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index 8f7ea3ba..4e6c8836 100644 --- a/packages/proxy/schema/model_list.json +++ b/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", diff --git a/packages/proxy/scripts/deprecated_model_ids.json b/packages/proxy/scripts/deprecated_model_ids.json index 1ccb7680..7778424f 100644 --- a/packages/proxy/scripts/deprecated_model_ids.json +++ b/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"