MindWorkAI/AI-Studio
1
0 Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-10-18 09:38:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Recognize the models which hold a connection open instead of chatting

Browse Source
This commit is contained in:
Thorsten Sommer committed 2026-09-19 16:58:05 +02:00
1 parent f7350bf86b
commit 987ccf527d
5 files changed
+62 -8
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

app/Tests/Models/Corpus/CapabilitySnapshot.txt
+1 -1
View File
@@ -64,7 +64,7 @@ FIREWORKS | accounts/fireworks/models/qwen3-235b-a22b | CHAT_COMPLETION_API, FUN
FIREWORKS | whisper-v3 | SPEECH_INPUT, TEXT_OUTPUT | TRANSCRIPTION | (unknown) | (unknown) | (unknown)
GOOGLE | gemini-1.0-pro-vision | CHAT_COMPLETION_API, MULTIPLE_IMAGE_INPUT, TEXT_INPUT, TEXT_OUTPUT | CHAT | (unknown) | (unknown) | (unknown)
GOOGLE | gemini-2.0-flash | AUDIO_INPUT, CHAT_COMPLETION_API, FUNCTION_CALLING, MULTIPLE_IMAGE_INPUT, SPEECH_INPUT, TEXT_INPUT, TEXT_OUTPUT, VIDEO_INPUT | CHAT | (unknown) | 3600 per request | PROVIDER_API countTokens
GOOGLE | gemini-2.0-flash-live-001 | AUDIO_INPUT, CHAT_COMPLETION_API, FUNCTION_CALLING, SPEECH_INPUT, SPEECH_OUTPUT, TEXT_INPUT, TEXT_OUTPUT, VIDEO_INPUT | CHAT | (unknown) | (unknown) | (unknown)
GOOGLE | gemini-2.0-flash-live-001 | AUDIO_INPUT, CHAT_COMPLETION_API, FUNCTION_CALLING, SPEECH_INPUT, SPEECH_OUTPUT, TEXT_INPUT, TEXT_OUTPUT, VIDEO_INPUT | REALTIME | (unknown) | (unknown) | (unknown)
GOOGLE | gemini-2.5-flash | ALWAYS_REASONING, AUDIO_INPUT, CHAT_COMPLETION_API, FUNCTION_CALLING, MULTIPLE_IMAGE_INPUT, SPEECH_INPUT, TEXT_INPUT, TEXT_OUTPUT, VIDEO_INPUT | CHAT | 1048576 | 3600 per request | PROVIDER_API countTokens
GOOGLE | gemini-2.5-flash-image | CHAT_COMPLETION_API, IMAGE_OUTPUT, MULTIPLE_IMAGE_INPUT, TEXT_INPUT, TEXT_OUTPUT | IMAGE_GENERATION | (unknown) | (unknown) | (unknown)
GOOGLE | gemini-2.5-flash-lite | AUDIO_INPUT, CHAT_COMPLETION_API, FUNCTION_CALLING, MULTIPLE_IMAGE_INPUT, OPTIONAL_REASONING, SPEECH_INPUT, TEXT_INPUT, TEXT_OUTPUT, VIDEO_INPUT | CHAT | 1048576 | 3600 per request | PROVIDER_API countTokens