DeepSeek V4 Pro
vichar-deepseek-v4-pro
DeepSeek V4 Pro, a cost-efficient tool-calling model for coding and agents.
- Context window
- 1.0M
- Max output
- 393k
- Input
- $0.66 /M tokens
- Output
- $1.98 /M tokens
Supported parameters
- temperature
- max_tokens
- top_p
- response_format
- reasoning_effort
- 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-v4-pro",
"messages": [{"role": "user", "content": "Hello"}]
}'