Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...
# Запрос к API VEGA через morph/morph-v3-large
curl https://api.vega.chat/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $VEGA_API_KEY" \
-d '{
"model": "morph/morph-v3-large",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'