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 Flash (Non-reasoning)2026-04-24DeepSeek: DeepSeek V4 Flash (free)2026-04-24DeepSeek V3.2 (Reasoning)2025-12-01DeepSeek: DeepSeek V3.22025-12-01
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
84
tokens/sec
Faster than 43% of models
1.10
seconds
Faster than 51% of models
1.10
seconds
Faster than 66% of models
Market Median
94 tok/s
11% slower
Median TTFT
1.11s
1% faster
Throughput/Dollar
154
tok/s per $/1M
Speed Comparison
DeepSeek: DeepSeek V4 Pro
84 tok/s-0%
Qwen: Qwen3.5-27B
84 tok/s+0%
GPT-5.5 (high)
83 tok/s-1%
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