DeepSeek V3.2
vichar-deepseek-v3.2
DeepSeek V3.2, a cost-efficient tool-calling model. A strong budget option for coding and agents.
- Context window
- 164k
- Max output
- 147k
- Input
- $0.26 /M tokens
- Output
- $0.80 /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-deepseek-v3.2",
"messages": [{"role": "user", "content": "Hello"}]
}'