LFM 2.5 2.6B
Experimentalvichar-lfm-2.5
Liquid LFM 2.5 2.6B, a compact edge-friendly model. Experimental: availability and rate limits may vary.
- Context window
- 66k
- Max output
- 8k
- Input
- $0.15 /M tokens
- Output
- $0.60 /M tokens
Supported parameters
- temperature
- max_tokens
- top_p
- frequency_penalty
- presence_penalty
- response_format
- tools
- tool_choice
- reasoning
curl https://api.vichar.io/v1/chat/completions \
-H "Authorization: Bearer $VICHAR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "vichar-lfm-2.5",
"messages": [{"role": "user", "content": "Hello"}]
}'