DeepSeek: DeepSeek V4 Flash 0731
DeepSeek
deepseek/deepseek-v4-flash-0731About this model
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Make a request
OpenAI-compatible: set the base URL and your Promptix API key, keep your existing SDK.
curl https://promptix.tn/api/v1/chat/completions \ -H "Authorization: Bearer $PROMPTIX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek/deepseek-v4-flash-0731", "messages": [ {"role": "user", "content": "Hello! What can you do?"} ] }'Pricing
In TND per 1M tokens. VAT and the platform fee are added at top-up.
Input tokens
0.081 TNDper 1M tokens
Output tokens
1.239 TNDper 1M tokens
1,000 requests with 1K input and 500 output tokens cost about 0.701 TND.
Specifications
- Provider
- DeepSeek
- Context window
- 1,310,720 tokens
- Input modality
- Text
- Added
- Jul 31, 2026
- Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penalty