Related Models
Pricing
Input
$0.05
per 1M tokens
Output
$0.40
per 1M tokens
Blended
$0.14
per 1M tokens
Cheaper than 78% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.14
Monthly
$4.14
vs. Similar Models
Nova 2.0 Lite (medium)Q:0.0
$0.85+516%
OpenAI: o3 MiniQ:0.0
$1.93+1295%
Qwen3.5 Omni FlashQ:0.0
$0.28+99%
OpenAI: o1-proQ:-0.1
$262.50+190117%
Performance
142
tokens/sec
Faster than 70% of models
40.04
seconds
Faster than 2% of models
40.04
seconds
Faster than 11% of models
Market Median
94 tok/s
52% faster
Median TTFT
1.10s
3524% slower
Throughput/Dollar
1031
tok/s per $/1M
Speed Comparison
Sarvam M (Reasoning)
143 tok/s+0%
Qwen3 VL 8B Instruct
143 tok/s+0%
Grok 4.3 (medium)
143 tok/s+0%
Benchmarks
MMLU-Pro
77.2%
GPQA Diamond
67.0%
HLE
7.6%
LiveCodeBench
76.3%
SciCode
33.8%
TerminalBench Hard
17.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
78.3%
IFBench
65.9%
Long Context Recall
40.0%
Tau2
30.4%
Market AverageTop Score