22 Commits
Author SHA1 Message Date
Father Bot b0ca129e75 Remove legacy gpt-3.5-turbo and gpt-4 models
Drop the remaining old models from the menu and config. The lineup is
now gpt-4o-mini (default), gpt-5.5, gpt-4o and the Claude models.
2026-05-20 12:09:55 +03:00
Father Bot 0dba82f04f Replace dalle-3 with gpt-image-1 in models.yml
Swap the image model entry to gpt-image-1 ($0.042 per 1024x1024
medium-quality image) so /balance reflects the new model.
2026-05-08 20:33:39 +03:00
Father Bot 169406c377 Replace dalle-2 with dall-e-3 pricing in models.yml
Update the image model entry to dalle-3 at $0.04 per 1024x1024 image
so /balance reflects DALL-E 3 costs.
2026-04-14 09:50:40 +03:00
Father Bot 04174251b5 Update gpt-4o pricing to current rates
gpt-4o was priced at its launch rate (0.005/0.015). OpenAI later cut
it to $2.50 / $10 per 1M tokens; update to 0.0025/0.01 so /balance
reflects current cost.
2026-04-05 16:42:21 +03:00
Father Bot c828549d7a Remove deprecated models from the menu
Drop gpt-3.5-turbo-16k, gpt-4-1106-preview and gpt-4-vision-preview
from available_text_models and their info blocks. All three are
deprecated/retired by OpenAI; gpt-4o and gpt-4o-mini cover their use
cases (including vision).
2026-04-02 10:14:03 +03:00
Father Bot e97a0819c1 Flag vision-capable models in models.yml
Add 'vision: true' to models that can read images: gpt-4o,
gpt-4o-mini, gpt-4-vision-preview, gpt-5.5 and the Claude models.
This lets the bot decide vision support from config instead of
hardcoded model names.
2026-03-25 16:20:33 +03:00
Father Bot 2ace648aa9 Add Anthropic Claude models via OpenRouter
Add Claude Opus 4.8, Claude Sonnet and Claude Haiku as selectable
chat models, routed through OpenRouter (provider: openrouter). Slugs
and pricing taken from the OpenRouter model list. Requires
openrouter_api_key to be set.
2026-03-15 10:28:36 +03:00
Father Bot dbe426775f Add OpenAI gpt-5.5 model (via OpenRouter)
Add OpenAI's latest flagship gpt-5.5 as a selectable model, routed
through OpenRouter (provider: openrouter, slug openai/gpt-5.5).
Pricing taken from the OpenRouter model list.
2026-03-09 17:14:53 +03:00
Father Bot 6b90a74567 Remove text-davinci-003 from models config
OpenAI shut down the legacy text-davinci-003 completions model in
early 2024, so it can no longer be used. Drop it from the available
models list and remove its info block.
2026-02-11 18:42:55 +03:00
Father Bot bdad62174d Default new users to gpt-4o-mini instead of gpt-3.5-turbo
The default model is taken from available_text_models[0] (used by
Database.add_new_user and the registration fallback). Move
gpt-4o-mini to the front so new users start on it; gpt-3.5-turbo is
outdated, while gpt-4o-mini is cheaper, smarter and supports vision.
This also makes it the first option in the /settings menu.
2026-01-06 11:30:18 +03:00
Father Bot cb4f55850a Fix typo in gpt-4-vision description (capabilties -> capabilities) 2025-12-13 17:41:55 +03:00
Father Bot 43aa46a872 Add gpt-4o-mini model support
Wire gpt-4o-mini through the bot: register it in models.yml
(available list + pricing/scores entry) and add it to the model
sets in openai_utils (chat, streaming, vision and token counting).
gpt-4o-mini is cheaper and smarter than gpt-3.5-turbo and supports
images, so it is a good default-grade option. Addresses #474.
2025-12-05 19:05:44 +03:00
Father Bot 148b3b8268 Normalize model score labels to capitalized form
gpt-4-1106-preview, gpt-4-vision-preview and gpt-4o used lowercase
score keys (smart/fast/cheap) while the rest used capitalized ones.
These keys are shown verbatim as labels in /settings, so normalize
them for consistent display.
2025-12-04 11:32:08 +03:00
Father Bot 7416a7edd6 Fix gpt-4o scores: it is faster and cheaper than gpt-4
gpt-4o was scored fast:2 cheap:2 (same as plain gpt-4), which is
misleading. Bump to fast:4 cheap:4 to reflect its actual profile.
2025-12-02 16:47:21 +03:00
Father Bot 3aab56a21a Fix incorrect gpt-4o pricing in models.yml
gpt-4o was priced at gpt-4 rates (0.03/0.06). Correct to actual
0.005/0.015 per 1k tokens so the /balance report is accurate.
2025-12-01 10:14:03 +03:00
pyranota fff2839327 Fix not showing GPT-4o in settings 2024-05-23 18:49:59 +02:00
pyranota 752f38b348 Add support for GPT-4o 2024-05-23 17:45:28 +02:00
OlegGoless 3b8b0b2a52 vision 2024-04-02 14:43:04 +02:00
Karim Iskakov 61b8dbd0ce Add GPT-4 Turbo 2023-11-15 17:45:57 +03:00
maccagnitandGitHub 533e6705c8 Added GPT-3.5 16K chat functionality (#306) 2023-06-20 11:47:19 +03:00
Karim IskakovandGitHub e421be1634 DALLE 2 2023-04-21 12:37:06 +03:00
Karim IskakovandGitHub a4b5eb36e1 GPT-4 support 2023-03-22 23:58:48 +03:00