All models1 shown
DeepSeek V4 Flash
DeepSeekdeepinfra/DeepSeek-V4-Flash
Released Apr 24, 2026
- providers
- 1
- context
- 1.0M
- max out
- 16.3K
- input /M
- $0.09
- output /M
- $0.18
also answers toDeepSeek-V4-FlashDeepSeek-V4-Flash-0731deepseek-v4-flash:0731deepseek-ai/deepseek-v4-flashdeepseek-ai/deepseek-v4-flash-0731deepseek/deepseek-v4-flash-20260423
About
- knowledge cutoff
- May 1, 2025
- open weights
- yes
- best for
- extractioncodingcompute
Capabilities
What the model accepts and returns, where a probe through our own gateway proved it.
- streaming
- tools
- json mode
- vision
- audio
Providers
What you pay through us for each provider, and its own list price where that differs.
DeepInfra
deepinfra/DeepSeek-V4-Flash- input /M
- $0.09
- output /M
- $0.18
1.0M context16.3K max out
Speed
- fastest over 24 hours
- 27.4 t/s
Fastest: DeepInfra
- DeepInfra1,359 ms to first token27.4 t/smedian of 23
Served
- served in the last 24 hours
- 100.00%
Across 1 provider, 24 of 24 requests
- DeepInfra100.00% · 24 of 24
Rebuilt once a day from the requests we sent, so it is a daily figure and not a live one.
not yet
Not yet. These figures come from Artificial Analysis, which the publish pipeline reads once a day.
Integrations
What the model holds, rather than a compatibility grade: nothing here measures how well a particular tool gets on with it, so nothing here scores one.
- answers on
- chat completions
- accepts
- text
- returns
- text
request parameters it takes
- reasoning
- response_format
- tool_choice
- tools
Use this model
Works with the OpenAI SDK. Point it at our base URL and use this id.
curl https://api.hopscotchlabs.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepinfra/DeepSeek-V4-Flash",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 256
}'