Related Models
Pricing
Input
$2.00
per 1M tokens
Output
$8.00
per 1M tokens
Blended
$3.50
per 1M tokens
Cheaper than 15% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.50
Monthly
$105.00
vs. Similar Models
Granite 4.0 H SmallQ:-0.1
$0.11-97%
Jamba 1.5 LargeQ:-0.2
$3.500%
Nous: Hermes 3 70B InstructQ:-0.2
$0.70-80%
Qwen3 8B (Non-reasoning)Q:-0.2
$0.18-95%
Performance
61
tokens/sec
Faster than 28% of models
0.86
seconds
Faster than 63% of models
0.86
seconds
Faster than 74% of models
Market Median
94 tok/s
35% slower
Median TTFT
1.11s
22% faster
Throughput/Dollar
17
tok/s per $/1M
Speed Comparison
Llama 3.2 Instruct 90B (Vision)
61 tok/s+0%
Jamba 1.6 Large
61 tok/s+0%
Qwen3 8B (Non-reasoning)
62 tok/s+1%
Benchmarks
MMLU-Pro
57.7%
GPQA Diamond
39.0%
HLE
3.8%
LiveCodeBench
18.1%
SciCode
18.8%
TerminalBench Hard
2.3%
MATH-500
60.0%
AIME
5.7%
AIME 2025
2.3%
IFBench
35.2%
Long Context Recall
17.3%
Tau2
13.5%
Market AverageTop Score