Related Models
Pricing
Input
$0.30
per 1M tokens
Output
$2.50
per 1M tokens
Blended
$0.85
per 1M tokens
Cheaper than 39% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.85
Monthly
$25.50
vs. Similar Models
Claude 3 OpusQ:0.0
$30.00+3429%
Devstral Small (May '25)Q:0.0
$0.07-91%
Magistral Small 1.2Q:+0.1
$0.75-12%
Sarvam 105B (high)Q:+0.1
$0.07-91%
Performance
219
tokens/sec
Faster than 90% of models
0.83
seconds
Faster than 65% of models
0.83
seconds
Faster than 75% of models
Market Median
94 tok/s
134% faster
Median TTFT
1.10s
25% faster
Throughput/Dollar
258
tok/s per $/1M
Speed Comparison
Nova 2.0 Omni (Non-reasoning)
219 tok/s-0%
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
220 tok/s+0%
OpenAI: GPT-4o
218 tok/s-1%
Benchmarks
MMLU-Pro
74.3%
GPQA Diamond
60.3%
HLE
3.0%
LiveCodeBench
34.6%
SciCode
24.0%
TerminalBench Hard
6.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
33.7%
IFBench
40.5%
Long Context Recall
17.7%
Tau2
62.0%
Market AverageTop Score