Related Models
DeepSeek: DeepSeek V4 Pro2026-04-24DeepSeek V4 Pro (Reasoning, High Effort)2026-04-24DeepSeek: DeepSeek V4 Flash2026-04-24DeepSeek V4 Flash (Reasoning, High Effort)2026-04-24DeepSeek V4 Pro (Non-reasoning)2026-04-24DeepSeek V4 Flash (Non-reasoning)2026-04-24DeepSeek: DeepSeek V4 Flash (free)2026-04-24DeepSeek V3.2 (Reasoning)2025-12-01
Pricing
Input
$0.28
per 1M tokens
Output
$0.41
per 1M tokens
Blended
$0.31
per 1M tokens
Cheaper than 61% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.31
Monthly
$9.30
vs. Similar Models
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)Q:0.0
$0.41+33%
Inception: Mercury 2Q:-0.1
$0.38+21%
Claude 4 Opus (Non-reasoning)Q:+0.1
$30.00+9577%
Claude 4 Sonnet (Non-reasoning)Q:+0.1
$6.00+1835%
Performance
80
tokens/sec
Faster than 39% of models
0.71
seconds
Faster than 69% of models
25.77
seconds
Faster than 18% of models
Market Median
94 tok/s
15% slower
Median TTFT
1.11s
36% faster
Throughput/Dollar
258
tok/s per $/1M
Speed Comparison
GPT-5 (low)
80 tok/s-0%
DeepSeek: DeepSeek V3.2
80 tok/s+1%
DeepSeek V3.2 Exp (Non-reasoning)
80 tok/s+1%
Benchmarks
MMLU-Pro
85.0%
GPQA Diamond
79.7%
HLE
13.8%
LiveCodeBench
78.9%
SciCode
37.7%
TerminalBench Hard
31.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
87.7%
IFBench
54.1%
Long Context Recall
69.0%
Tau2
33.9%
Market AverageTop Score