← All models
Try in Chat
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731
DeepSeek V4 Flash pinned snapshot 0731. Fast, low-cost reasoning model with tool calling.
chatreasoningcodetools
pricing
this model runs at 3 EU providers. you pay the price of the provider that serves your request, ozeye's margin included. the usage dashboard shows which provider served each request, and you can block providers in your settings. prices excl. VAT.
| provider | location | input | cached input | output | context window |
|---|---|---|---|---|---|
| Inceptron | Lund, Sweden | €0.1245/M | €0.0287/M | €0.2682/M | 1M |
| TensorX | Dublin, Ireland | €0.2395/M | €0.0599/M | €0.2874/M | 1M |
| Scaleway | Paris, France | €0.4480/M | €0.0896/M | €0.8960/M | 262K |
Inceptron Lund, Sweden
- input
- €0.1245/M
- cached input
- €0.0287/M
- output
- €0.2682/M
- context
- 1M
TensorX Dublin, Ireland
- input
- €0.2395/M
- cached input
- €0.0599/M
- output
- €0.2874/M
- context
- 1M
Scaleway Paris, France
- input
- €0.4480/M
- cached input
- €0.0896/M
- output
- €0.8960/M
- context
- 262K
Specifications
Context window
1M
Providers
3
Released
Jul 2026
Try DeepSeek V4 Flash 0731
Use this model directly in the ozeye chat interface.
Benchmarks
Loading benchmarks...
Latency
Loading latency data...
API
curl https://ozeye.ai/v1/chat/completions \
-H "Authorization: Bearer $OZEYE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash-0731",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'