Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.25
per 1M tokens
Cheaper than 66% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.25
Monthly
$7.50
vs. Similar Models
Qwen3 1.7B (Reasoning)Q:0.0
$0.40+59%
Jamba 1.5 MiniQ:+0.1
$0.250%
Olmo 3 7B InstructQ:+0.2
$0.13-50%
Apertus 70B InstructQ:-0.2
$1.34+438%
Performance
185
tokens/sec
Faster than 84% of models
0.84
seconds
Faster than 65% of models
0.84
seconds
Faster than 75% of models
Market Median
94 tok/s
98% faster
Median TTFT
1.10s
24% faster
Throughput/Dollar
741
tok/s per $/1M
Speed Comparison
Qwen3 Next 80B A3B (Reasoning)
186 tok/s+0%
Qwen3.5 35B A3B (Non-reasoning)
191 tok/s+3%
Nova 2.0 Lite (low)
179 tok/s-3%
Benchmarks
MMLU-Pro
36.7%
GPQA Diamond
30.0%
HLE
4.6%
LiveCodeBench
7.1%
SciCode
10.1%
TerminalBench HardNot evaluated
MATH-500
25.7%
AIME
3.3%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score