Model catalog

Models by provider, mode, and modality.

Use exact model IDs for new integrations. Legacy aliases remain accepted for compatibility, while public docs keep routing details internal.

ModelProviderModeModalitiesPrice
viable-2
/v1/chat/completions
VIABLE Labchat
textimagefiletext
$0.1 input / $0.4 output per 1M tokens
gpt-4.1-nano
/v1/chat/completions
OpenAIchat
textimagefilepdftext
$0.1 input / $0.4 output per 1M tokens
gemini-2.5-flash
/v1/chat/completions
Googlechat
textimagefilepdftext
$0.3 input / $2.5 output per 1M tokens
gpt-oss-120b
/v1/chat/completions
Open weightsReasoning
VIABLE Labchat
texttext
$0.06 input / $0.15 output per 1M tokens
gpt-oss-20b
/v1/chat/completions
Open weightsReasoning
VIABLE Labchat
texttext
$0.03 input / $0.07 output per 1M tokens
gemma-4-31b-it
/v1/chat/completions
Open weightsReasoning
VIABLE Labchat
textimagetext
$0.12 input / $0.36 output per 1M tokens
nemotron-3-super-120b-a12b
/v1/chat/completions
Open weightsReasoning
VIABLE Labchat
texttext
$0.06 input / $0.24 output per 1M tokens
llama-3.1-8b-instruct
/v1/chat/completions
Open weights
VIABLE Labchat
texttext
$0.22 input / $0.22 output per 1M tokens
llama-3.1-70b-instruct
/v1/chat/completions
Open weights
VIABLE Labchat
texttext
$0.4 input / $0.4 output per 1M tokens
nomic-embed-text-v1.5
/v1/embeddings
Open weights
VIABLE Labembedding
textembedding
$0.005 input / n/a output per 1M tokens
flux.2-klein
/v1/images/generations
Open weights
VIABLE Labimage generation
textimage
$0.014 per image
whisper-large-v3
/v1/audio/transcriptions
Open weights
VIABLE Labaudio transcription
audiofiletext
$0.006 per min
gpt-4o-transcribe
/v1/audio/transcriptions
OpenAIaudio transcription
audiofiletext
$0.006 per min
gpt-4o-mini-tts
/v1/audio/speech
OpenAIaudio speech
textaudio
$0.6 text input / $12 audio output per 1M tokens · fallback $0.015/min
kokoro
/v1/audio/speech
Open weights
VIABLE Labaudio speech
textaudio
$0.006 per min