Pricing
Input
$0.50
per 1M tokens
Output
$1.50
per 1M tokens
Blended
$0.75
per 1M tokens
Cheaper than 44% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.75
Monthly
$22.50
vs. Similar Models
Sarvam 105B (high)Q:0.0
$0.07-90%
Claude 3 OpusQ:-0.1
$30.00+3900%
Devstral Small (May '25)Q:-0.1
$0.07-90%
Nova 2.0 Lite (Non-reasoning)Q:-0.1
$0.85+13%
Performance
82
tokens/sec
Faster than 42% of models
0.51
seconds
Faster than 86% of models
24.91
seconds
Faster than 20% of models
Market Median
94 tok/s
12% slower
Median TTFT
1.10s
54% faster
Throughput/Dollar
109
tok/s per $/1M
Speed Comparison
GPT-5.5 (high)
82 tok/s+0%
Grok 4.1 Fast (Non-reasoning)
83 tok/s+1%
Qwen: Qwen3.5-27B
83 tok/s+1%
Benchmarks
MMLU-Pro
76.8%
GPQA Diamond
66.3%
HLE
6.1%
LiveCodeBench
72.3%
SciCode
35.2%
TerminalBench Hard
4.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
80.3%
IFBench
44.4%
Long Context Recall
16.3%
Tau2
27.8%
Market AverageTop Score