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: DeepSeek V4 Flash (free)2026-04-24DeepSeek V3.2 (Reasoning)2025-12-01DeepSeek: DeepSeek V3.22025-12-01
Pricing
Input
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Blended
$0.17
per 1M tokens
Cheaper than 72% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.17
Monthly
$5.25
vs. Similar Models
MiniMax: MiniMax M2Q:-0.4
$0.44+152%
Claude 4.1 Opus (Non-reasoning)Q:-0.5
$30.00+17043%
Qwen3.5 122B A10B (Non-reasoning)Q:-0.6
$1.10+529%
Qwen: Qwen3.5-35B-A3BQ:+0.6
$0.35+103%
Performance
94
tokens/sec
Faster than 50% of models
0.96
seconds
Faster than 58% of models
0.96
seconds
Faster than 70% of models
Market Median
94 tok/s
0% slower
Median TTFT
1.11s
13% faster
Throughput/Dollar
539
tok/s per $/1M
Speed Comparison
OpenAI: GPT-5.1
95 tok/s+0%
MiMo-V2-Flash (Non-reasoning)
95 tok/s+0%
Reka Flash 3
95 tok/s+1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
71.6%
HLE
7.0%
LiveCodeBenchNot evaluated
SciCode
37.3%
TerminalBench Hard
34.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
47.2%
Long Context Recall
33.3%
Tau2
94.4%
Market AverageTop Score