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 3.2 Instruct 90B (Vision)Q:0.0
$1.38+820%
Qwen2.5 TurboQ:+0.1
$0.09-41%
Reka Flash (Sep '24)Q:+0.1
$0.35+133%
Llama 3.1 Instruct 8BQ:-0.1
$0.10-33%
Performance
77
tokens/sec
Faster than 38% of models
0.77
seconds
Faster than 68% of models
0.77
seconds
Faster than 77% of models
Market Median
94 tok/s
18% slower
Median TTFT
1.10s
31% faster
Throughput/Dollar
511
tok/s per $/1M
Speed Comparison
OpenAI: GPT-4o-mini
77 tok/s+1%
Olmo 3 7B Instruct
76 tok/s-1%
Anthropic: Claude Fable 5
77 tok/s+1%
Benchmarks
MMLU-ProNot evaluated
GPQA DiamondNot evaluated
HLENot evaluated
LiveCodeBenchNot evaluated
SciCodeNot evaluated
TerminalBench HardNot evaluated
MATH-500
33.1%
AIMENot evaluated
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2
20.2%
Market AverageTop Score