Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.23
per 1M tokens
Blended
$0.21
per 1M tokens
Cheaper than 69% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.21
Monthly
$6.18
vs. Similar Models
Command-R (Mar '24)Q:0.0
$0.75+264%
Apertus 70B InstructQ:+0.3
$1.34+553%
Mixtral 8x7B InstructQ:+0.3
$0.51+149%
Granite 3.3 8B (Non-reasoning)Q:-0.3
$0.09-59%
Performance
82
tokens/sec
Faster than 42% of models
0.45
seconds
Faster than 91% of models
0.45
seconds
Faster than 94% of models
Market Median
94 tok/s
13% slower
Median TTFT
1.11s
59% faster
Throughput/Dollar
400
tok/s per $/1M
Speed Comparison
Llama 3.1 Instruct 405B
82 tok/s-0%
Ministral 3 8B
83 tok/s+0%
Grok 4.1 Fast (Non-reasoning)
83 tok/s+1%
Benchmarks
MMLU-Pro
24.5%
GPQA Diamond
17.7%
HLE
4.3%
LiveCodeBench
4.6%
SciCode
2.4%
TerminalBench HardNot evaluated
MATH-500
12.1%
AIME
0.0%
AIME 2025Not evaluated
IFBench
19.9%
Long Context Recall
0.0%
Tau2
0.0%
Market AverageTop Score