Related Models
Pricing
Input
$0.30
per 1M tokens
Output
$2.50
per 1M tokens
Blended
$0.85
per 1M tokens
Cheaper than 39% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.85
Monthly
$25.50
vs. Similar Models
GPT-5 nano (medium)Q:0.0
$0.14-84%
OpenAI: o3 MiniQ:0.0
$1.93+126%
Qwen3.5 Omni FlashQ:0.0
$0.28-68%
OpenAI: o1-proQ:-0.1
$262.50+30782%
Performance
184
tokens/sec
Faster than 84% of models
12.31
seconds
Faster than 10% of models
23.17
seconds
Faster than 22% of models
Market Median
94 tok/s
95% faster
Median TTFT
1.11s
1006% slower
Throughput/Dollar
217
tok/s per $/1M
Speed Comparison
StepFun: Step 3.5 Flash
184 tok/s-0%
Nemotron 3 Ultra 550B A55B (Reasoning)
183 tok/s-1%
Jamba 1.6 Mini
185 tok/s+1%
Benchmarks
MMLU-Pro
81.3%
GPQA Diamond
76.8%
HLE
8.6%
LiveCodeBench
66.3%
SciCode
36.8%
TerminalBench Hard
17.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
88.7%
IFBench
68.5%
Long Context Recall
58.3%
Tau2
75.7%
Market AverageTop Score