From d15efc9c1be088de7b97bfdb658858788cb2b410 Mon Sep 17 00:00:00 2001 From: Teknium <127238744+teknium1@users.noreply.github.com> Date: Mon, 13 Apr 2026 19:22:23 -0700 Subject: [PATCH] fix: correct GPT-5 family context lengths in fallback defaults (#9309) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The generic 'gpt-5' fallback was set to 128,000 — which is the max OUTPUT tokens, not the context window. GPT-5 base and most variants (codex, mini) have 400,000 context. This caused /model to report 128k for models like gpt-5.3-codex when models.dev was unavailable. Added specific entries for GPT-5 variants with different context sizes: - gpt-5.4, gpt-5.4-pro: 1,050,000 (1.05M) - gpt-5.4-mini, gpt-5.4-nano: 400,000 - gpt-5.3-codex-spark: 128,000 (reduced) - gpt-5.1-chat: 128,000 (chat variant) - gpt-5 (catch-all): 400,000 Sources: https://developers.openai.com/api/docs/models --- agent/model_metadata.py | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/agent/model_metadata.py b/agent/model_metadata.py index 98bb9543fb..842373c1eb 100644 --- a/agent/model_metadata.py +++ b/agent/model_metadata.py @@ -106,9 +106,15 @@ DEFAULT_CONTEXT_LENGTHS = { "claude-sonnet-4.6": 1000000, # Catch-all for older Claude models (must sort after specific entries) "claude": 200000, - # OpenAI + # OpenAI — GPT-5 family (most have 400k; specific overrides first) + # Source: https://developers.openai.com/api/docs/models + "gpt-5.4-nano": 400000, # 400k (not 1.05M like full 5.4) + "gpt-5.4-mini": 400000, # 400k (not 1.05M like full 5.4) + "gpt-5.4": 1050000, # GPT-5.4, GPT-5.4 Pro (1.05M context) + "gpt-5.3-codex-spark": 128000, # Spark variant has reduced 128k context + "gpt-5.1-chat": 128000, # Chat variant has 128k context + "gpt-5": 400000, # GPT-5.x base, mini, codex variants (400k) "gpt-4.1": 1047576, - "gpt-5": 128000, "gpt-4": 128000, # Google "gemini": 1048576,