Repository navigation
Replace retiring OpenAI models in library defaults, tools, and README - #382
Merged
Merged
Conversation
OpenAI retires gpt-4o, gpt-4o-mini, gpt-4.1 and gpt-4.1-mini on Jan 14th 2027. Default forecasting llms move to gpt-6-sol, small-model uses to gpt-6-luna (OpenAI routes) or Claude Haiku 5.5 (OpenRouter/Anthropic routes). Also replaces the gpt-4o-search-preview default researcher and the Claude 3.x defaults on the Anthropic route. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Adds a date question so every forecastable type is covered. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
OpenAI retires
gpt-4o,gpt-4o-mini,gpt-4.1andgpt-4.1-minion Jan 14th 2027. This replaces them in library defaults, tools, the current template's examples, and the README. Bot definitions inrun_bots.pyand historical templates/experiments are unchanged.ForecastBot._llm_config_defaults(by key route)gpt-6-sol(wasgpt-4o)openrouter/openai/gpt-6-solanthropic/claude-sonnet-5-5(wasclaude-3-7-sonnet-latest)metaculus/gpt-6-solgpt-6-luna(wasgpt-4o-mini)openrouter/anthropic/claude-haiku-5.5anthropic/claude-haiku-5-5(wasclaude-3-5-sonnet-20241022)metaculus/gpt-6-lunaopenai/gpt-5-search-api(wasgpt-4o-search-preview)openrouter/perplexity/sonar-pro(gpt-4o-search-previewis no longer listed on OpenRouter)metaculus/gpt-5-search-apigpt-6 models are created with
temperature=Nonesince they reject temperature.Other changes
GeneralLlmdefault timeout table: addedgpt-6→ 120s (same asgpt-5); without it the new defaults would fall back to 60sMainBotsummarizer,SmartSearcher,DataAnalyzer,TopicGenerator, intervention-testing policy agent and resolver defaultsopenai/gpt-4.1+gpt-4oreplaced byopenai/gpt-6-soltemplate_bot_2026_fall.pyexamplellms(and example timeout 40 → 160s for a reasoning model)template_bot_2026_fall.pyEXAMPLE_QUESTIONSnow use bot-testing-area questions, and a date question was addedTesting
gpt-4o-search-previewis absent from OpenRouter's model listTemplateBot()with nollmson the OpenRouter route forecast binary, multiple choice and numeric example questions end to endllm-proxy.metaculus.comdoes not currently resolve🤖 Generated with Claude Code