Skip to main content
Back to Explore

DeepSeek V4 Pro (Non-reasoning)

DeepSeek·Released 2026-04-24
Open Source

Pricing

Input

$0.43

per 1M tokens

Output

$0.87

per 1M tokens

Blended

$0.54

per 1M tokens

Cheaper than 49% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.54

Monthly

$16.32

vs. Similar Models

GPT-5 (low)Q:0.0
$3.44+532%
MiMo-V2-Flash (Reasoning)Q:0.0
$0.15-72%
MiniMax: MiniMax M2.1Q:+0.2
$0.45-16%
Claude 4 Opus (Reasoning)Q:-0.2
$30.00+5415%

Performance

73

tokens/sec

Faster than 36% of models

1.10

seconds

Faster than 50% of models

1.10

seconds

Faster than 65% of models

Market Median

94 tok/s

23% slower

Median TTFT

1.10s

0% slower

Throughput/Dollar

133

tok/s per $/1M

Speed Comparison

GPT-5.2 (Non-reasoning)
73 tok/s+1%
Nova Premier
71 tok/s-2%
DeepSeek V4 Pro (Reasoning, High Effort)
74 tok/s+2%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
71.7%
HLE
7.7%
LiveCodeBenchNot evaluated
SciCode
42.4%
TerminalBench Hard
36.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
45.8%
Long Context Recall
45.0%
Tau2
91.2%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models