Related Models
Pricing
Input
$1.25
per 1M tokens
Output
$10.00
per 1M tokens
Blended
$3.44
per 1M tokens
Cheaper than 17% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.44
Monthly
$103.14
vs. Similar Models
Qwen3.5 9B (Non-reasoning)Q:-0.1
$0.08-98%
Qwen3 VL 235B A22B (Reasoning)Q:+0.2
$2.17-37%
Qwen3.5 4BQ:-0.3
$0.06-98%
DeepSeek: R1Q:-0.3
$1.15-67%
Performance
101
tokens/sec
Faster than 54% of models
0.72
seconds
Faster than 69% of models
0.72
seconds
Faster than 78% of models
Market Median
94 tok/s
7% faster
Median TTFT
1.11s
36% faster
Throughput/Dollar
29
tok/s per $/1M
Speed Comparison
GPT-5 mini (minimal)
101 tok/s-0%
OpenAI: GPT-4.1 Mini
101 tok/s+0%
Meta: Llama 4 Maverick
100 tok/s-1%
Benchmarks
MMLU-Pro
80.1%
GPQA Diamond
64.3%
HLE
5.2%
LiveCodeBench
49.4%
SciCode
36.5%
TerminalBench Hard
22.7%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
38.0%
IFBench
43.2%
Long Context Recall
44.0%
Tau2
46.5%
Market AverageTop Score