Provider ranking
1 ranking rows
Models in this family
3 models
DeepSeek V4 Pro (Non-reasoning)
9 evaluationsDeepSeek
This is the non-reasoning variant of the DeepSeek V4 Pro model. It retains the core capabilities of the V4 Pro series, such as strong coding and general knowledge, but is optimized for faster response times and lower cost by omitting the extended reasoning or chain-of-thought process. It is suitable for applications requiring quick, cost-effective responses.
Input / 1M tokens
$1.74
Output / 1M tokens
$3.48
DeepSeek V4 Pro (Reasoning, High Effort)
9 evaluationsDeepSeek
A high-effort reasoning model from the DeepSeek V4 series, optimized for complex problem-solving and deep analytical tasks. It likely employs extended thinking or chain-of-thought processes to tackle challenging queries in coding, mathematics, and logic.
Input / 1M tokens
$1.74
Output / 1M tokens
$3.48
DeepSeek V4 Pro (Reasoning, Max Effort)
9 evaluationsDeepSeek
DeepSeek V4 Pro is a high-compute reasoning model optimized for complex logical, mathematical, and coding tasks. It represents the 'Max Effort' variant, utilizing significant computational resources to maximize accuracy and depth in its reasoning chains.
Input / 1M tokens
$1.74
Output / 1M tokens
$3.48
Discussion

Thinking... Make sure you are connected to GitHub server

