diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index 349a1ee9..5483840e 100644 --- a/packages/proxy/schema/index.ts +++ b/packages/proxy/schema/index.ts @@ -1034,7 +1034,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = { "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-20b": ["groq"], // NOTE: We use groq pricing for this and Together pricing for the 120B model + "openai/gpt-oss-20b": ["groq", "together"], "o4-mini-deep-research-2025-06-26": ["openai", "azure"], "o4-mini-deep-research": ["openai", "azure"], "o3-deep-research-2025-06-26": ["openai", "azure"], diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index 89b6c9ac..a8df77ac 100644 --- a/packages/proxy/schema/model_list.json +++ b/packages/proxy/schema/model_list.json @@ -5934,8 +5934,8 @@ "openai/gpt-oss-20b": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.075, - "output_cost_per_mil_tokens": 0.3, + "input_cost_per_mil_tokens": 0.05, + "output_cost_per_mil_tokens": 0.2, "input_cache_read_cost_per_mil_tokens": 0.0375, "displayName": "OpenAI GPT-OSS (20B)", "reasoning": true,