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
DeepSeek: DeepSeek V3.1 TerminusQ:+0.1
$0.44+42%
Qwen: Qwen3 Coder NextQ:-0.1
$0.28-9%
Grok Code Fast 1Q:+0.3
$0.53+69%
DeepSeek V3.1 (Non-reasoning)Q:-0.3
$0.83+169%
Performance
80
tokens/sec
Faster than 41% of models
0.80
seconds
Faster than 66% of models
0.80
seconds
Faster than 76% of models
Market Median
94 tok/s
14% slower
Median TTFT
1.10s
28% faster
Throughput/Dollar
259
tok/s per $/1M
Speed Comparison
DeepSeek: DeepSeek V3.2
80 tok/s-0%
OpenAI: GPT-5.5
80 tok/s-0%
Llama 3.1 Instruct 405B
81 tok/s+0%
Benchmarks
MMLU-Pro
83.6%
GPQA Diamond
73.8%
HLE
8.6%
LiveCodeBench
55.4%
SciCode
39.9%
TerminalBench Hard
25.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
57.7%
IFBench
43.1%
Long Context Recall
43.0%
Tau2
33.9%
Market AverageTop Score