From 16b813669e89ea2fd0e6089df27ffde17b3c47d5 Mon Sep 17 00:00:00 2001 From: cpinn <4450689+cpinn@users.noreply.github.com> Date: Tue, 19 May 2026 23:49:27 +0000 Subject: [PATCH 1/2] fix: update Groq model metadata for openai/gpt-oss-120b --- packages/proxy/schema/index.ts | 2 +- packages/proxy/schema/model_list.json | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index 082478cd..a7afa5ad 100644 --- a/packages/proxy/schema/index.ts +++ b/packages/proxy/schema/index.ts @@ -957,7 +957,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = { "databricks-meta-llama-3-3-70b-instruct": ["databricks"], "databricks-meta-llama-3-1-405b-instruct": ["databricks"], "databricks-meta-llama-3-1-8b-instruct": ["databricks"], - "openai/gpt-oss-120b": ["together", "groq", "baseten"], + "openai/gpt-oss-120b": ["groq","together","baseten"], "openai/gpt-oss-20b": ["groq"], // NOTE: We use groq pricing for this and Together pricing for the 120B model "o4-mini-deep-research-2025-06-26": ["openai", "azure"], "o4-mini-deep-research": ["openai", "azure"], diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index 23f79b46..d2c225c7 100644 --- a/packages/proxy/schema/model_list.json +++ b/packages/proxy/schema/model_list.json @@ -1532,13 +1532,13 @@ "openai/gpt-oss-120b": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.1, - "output_cost_per_mil_tokens": 0.5, + "input_cost_per_mil_tokens": 0.15, + "output_cost_per_mil_tokens": 0.6, "input_cache_read_cost_per_mil_tokens": 0.075, "displayName": "OpenAI GPT-OSS (120B)", "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 32766, + "max_output_tokens": 65536, "available_providers": [ "groq", "together", From c8bb095cd67e92e0c2d5c94000a43261a24cb3c8 Mon Sep 17 00:00:00 2001 From: Erin McNulty Date: Wed, 20 May 2026 10:00:34 -0400 Subject: [PATCH 2/2] undo model order change --- packages/proxy/schema/index.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index a7afa5ad..082478cd 100644 --- a/packages/proxy/schema/index.ts +++ b/packages/proxy/schema/index.ts @@ -957,7 +957,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = { "databricks-meta-llama-3-3-70b-instruct": ["databricks"], "databricks-meta-llama-3-1-405b-instruct": ["databricks"], "databricks-meta-llama-3-1-8b-instruct": ["databricks"], - "openai/gpt-oss-120b": ["groq","together","baseten"], + "openai/gpt-oss-120b": ["together", "groq", "baseten"], "openai/gpt-oss-20b": ["groq"], // NOTE: We use groq pricing for this and Together pricing for the 120B model "o4-mini-deep-research-2025-06-26": ["openai", "azure"], "o4-mini-deep-research": ["openai", "azure"],