Related Models
Pricing
Input
$0.15
per 1M tokens
Output
$0.15
per 1M tokens
Blended
$0.15
per 1M tokens
Cheaper than 75% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.15
Monthly
$4.50
vs. Similar Models
Llama 2 Chat 7BQ:+0.1
$0.10-33%
Reka Flash 3Q:-0.1
$0.13-17%
Mistral LargeQ:+0.2
$3.00+1900%
Qwen3.5 0.8B (Non-reasoning)Q:+0.2
$0.02-87%
Performance
52
tokens/sec
Faster than 20% of models
0.63
seconds
Faster than 74% of models
0.63
seconds
Faster than 82% of models
Market Median
94 tok/s
45% slower
Median TTFT
1.10s
43% faster
Throughput/Dollar
346
tok/s per $/1M
Speed Comparison
Qwen3.5 397B A17B (Non-reasoning)
52 tok/s-0%
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
52 tok/s-0%
Claude 4.5 Sonnet (Non-reasoning)
52 tok/s-0%
Benchmarks
MMLU-Pro
34.7%
GPQA Diamond
25.5%
HLE
5.2%
LiveCodeBench
8.3%
SciCode
5.2%
TerminalBench HardNot evaluated
MATH-500
48.9%
AIME
6.7%
AIME 2025
3.3%
IFBench
26.2%
Long Context Recall
2.0%
Tau2
21.1%
Market AverageTop Score