Skip to content

Update gpt-5 capabilities #345

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 15, 2025
Merged

Update gpt-5 capabilities #345

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
efb481d
Update gpt-5 capabilities
mnort9 Aug 13, 2025
e5c0874
Merge branch 'main' into gpt-5-capabilities
crmne Sep 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 15 additions & 7 deletions lib/ruby_llm/providers/openai/capabilities.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,9 @@ module Capabilities
gpt4o_realtime: /^gpt-4o-realtime/,
gpt4o_search: /^gpt-4o-search/,
gpt4o_transcribe: /^gpt-4o-transcribe/,
gpt5: /^gpt-5/,
gpt5_mini: /^gpt-5-mini/,
gpt5_nano: /^gpt-5-nano/,
o1: /^o1(?!-(?:mini|pro))/,
o1_mini: /^o1-mini/,
o1_pro: /^o1-pro/,
Expand All @@ -44,7 +47,7 @@ module Capabilities
def context_window_for(model_id)
case model_family(model_id)
when 'gpt41', 'gpt41_mini', 'gpt41_nano' then 1_047_576
when 'chatgpt4o', 'gpt4_turbo', 'gpt4o', 'gpt4o_audio', 'gpt4o_mini',
when 'gpt5', 'gpt5_mini', 'gpt5_nano', 'chatgpt4o', 'gpt4_turbo', 'gpt4o', 'gpt4o_audio', 'gpt4o_mini',
'gpt4o_mini_audio', 'gpt4o_mini_realtime', 'gpt4o_realtime',
'gpt4o_search', 'gpt4o_transcribe', 'gpt4o_mini_search', 'o1_mini' then 128_000
when 'gpt4' then 8_192
Expand All @@ -59,6 +62,7 @@ def context_window_for(model_id)

def max_tokens_for(model_id)
case model_family(model_id)
when 'gpt5', 'gpt5_mini', 'gpt5_nano' then 400_000
when 'gpt41', 'gpt41_mini', 'gpt41_nano' then 32_768
when 'chatgpt4o', 'gpt4o', 'gpt4o_mini', 'gpt4o_mini_search' then 16_384
when 'babbage', 'davinci' then 16_384 # rubocop:disable Lint/DuplicateBranch
Expand All @@ -76,16 +80,17 @@ def max_tokens_for(model_id)

def supports_vision?(model_id)
case model_family(model_id)
when 'gpt41', 'gpt41_mini', 'gpt41_nano', 'chatgpt4o', 'gpt4', 'gpt4_turbo', 'gpt4o', 'gpt4o_mini', 'o1',
'o1_pro', 'moderation', 'gpt4o_search', 'gpt4o_mini_search' then true
when 'gpt5', 'gpt5_mini', 'gpt5_nano', 'gpt41', 'gpt41_mini', 'gpt41_nano', 'chatgpt4o', 'gpt4',
'gpt4_turbo', 'gpt4o', 'gpt4o_mini', 'o1', 'o1_pro', 'moderation', 'gpt4o_search',
'gpt4o_mini_search' then true
else false
end
end

def supports_functions?(model_id)
case model_family(model_id)
when 'gpt41', 'gpt41_mini', 'gpt41_nano', 'gpt4', 'gpt4_turbo', 'gpt4o', 'gpt4o_mini', 'o1', 'o1_pro',
'o3_mini' then true
when 'gpt5', 'gpt5_mini', 'gpt5_nano', 'gpt41', 'gpt41_mini', 'gpt41_nano', 'gpt4', 'gpt4_turbo', 'gpt4o',
'gpt4o_mini', 'o1', 'o1_pro', 'o3_mini' then true
when 'chatgpt4o', 'gpt35_turbo', 'o1_mini', 'gpt4o_mini_tts',
'gpt4o_transcribe', 'gpt4o_search', 'gpt4o_mini_search' then false
else false # rubocop:disable Lint/DuplicateBranch
Expand All @@ -94,8 +99,8 @@ def supports_functions?(model_id)

def supports_structured_output?(model_id)
case model_family(model_id)
when 'gpt41', 'gpt41_mini', 'gpt41_nano', 'chatgpt4o', 'gpt4o', 'gpt4o_mini', 'o1', 'o1_pro',
'o3_mini' then true
when 'gpt5', 'gpt5_mini', 'gpt5_nano', 'gpt41', 'gpt41_mini', 'gpt41_nano', 'chatgpt4o', 'gpt4o',
'gpt4o_mini', 'o1', 'o1_pro', 'o3_mini' then true
else false
end
end
Expand All @@ -105,6 +110,9 @@ def supports_json_mode?(model_id)
end

PRICES = {
gpt5: { input: 1.25, output: 10.0, cached_input: 0.125 },
gpt5_mini: { input: 0.25, output: 2.0, cached_input: 0.025 },
gpt5_nano: { input: 0.05, output: 0.4, cached_input: 0.005 },
gpt41: { input: 2.0, output: 8.0, cached_input: 0.5 },
gpt41_mini: { input: 0.4, output: 1.6, cached_input: 0.1 },
gpt41_nano: { input: 0.1, output: 0.4 },
Expand Down