DeepSeek V4 Pro 0424 (Non-reasoning)

Benchmark scores, pricing, speed and comparisons for DeepSeek V4 Pro 0424 (Non-reasoning).

DeepSeek V4 Pro 0424 (Non-reasoning) is an AI model from DeepSeek, released 2026-04-24.

DeepSeek V4 Pro 0424 (Non-reasoning) at a glance

DeepSeek released DeepSeek V4 Pro 0424 (Non-reasoning) on April 24, 2026.

It costs $1.74 per million input tokens and $3.48 per million output tokens, so a sample workload of 1 million input tokens and 200,000 output tokens costs about $2.44. It writes about 172 output tokens per second, so a 500-token answer takes roughly 2.9 seconds once output starts, after a wait of about 1.54 seconds for the first token.

The benchmark data has no Intelligence Index, Coding Index, Math Index or individual benchmark results for DeepSeek V4 Pro 0424 (Non-reasoning) yet.

Every pair of models in the catalogue has a head-to-head page. Pick DeepSeek V4 Pro 0424 (Non-reasoning) and a rival on the model comparisons page to compare their scores, prices and speed side by side.

Key scores

Speed172.1Tokens/sec

No benchmark scores are available for this model yet.