From e650f398218ff160d1206df9a0839b78d95ebd85 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Hampus=20N=C3=A4sstr=C3=B6m?= Date: Sun, 12 Oct 2025 02:51:27 +0200 Subject: [PATCH] Reduce claude-4-sonnet max_output_tokens to 64k (#15409) Claude 4 Sonnet doesn't support more than 64k output tokens: https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/sonnet-4 --- model_prices_and_context_window.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6b2de335f66..645ecb9779f 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4841,7 +4841,7 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, - "max_output_tokens": 1000000, + "max_output_tokens": 64000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.5e-05,