Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.60
per 1M tokens
Blended
$0.30
per 1M tokens
Cheaper than 62% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.30
Monthly
$9.00
vs. Similar Models
Claude 3 SonnetQ:0.0
$6.00+1900%
Nova MicroQ:0.0
$0.06-80%
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)Q:-0.1
$0.300%
Microsoft: Phi 4Q:+0.2
$0.09-71%
Performance
154
tokens/sec
Faster than 76% of models
0.53
seconds
Faster than 85% of models
0.53
seconds
Faster than 90% of models
Market Median
95 tok/s
63% faster
Median TTFT
1.11s
52% faster
Throughput/Dollar
514
tok/s per $/1M
Speed Comparison
Mistral Small (Feb '24)
153 tok/s-1%
Nova 2.0 Pro Preview (Non-reasoning)
153 tok/s-1%
Sarvam 105B (high)
153 tok/s-1%
Benchmarks
MMLU-Pro
52.9%
GPQA Diamond
38.1%
HLE
4.3%
LiveCodeBench
14.1%
SciCode
15.6%
TerminalBench HardNot evaluated
MATH-500
56.3%
AIME
6.3%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score