Related Models
Pricing
Input
$0.04
per 1M tokens
Output
$0.14
per 1M tokens
Blended
$0.06
per 1M tokens
Cheaper than 88% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.06
Monthly
$1.83
vs. Similar Models
Claude 3 SonnetQ:0.0
$6.00+9736%
Mistral Small (Sep '24)Q:0.0
$0.30+392%
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)Q:-0.1
$0.30+392%
Microsoft: Phi 4Q:+0.2
$0.09+43%
Performance
262
tokens/sec
Faster than 94% of models
0.64
seconds
Faster than 74% of models
0.64
seconds
Faster than 82% of models
Market Median
94 tok/s
180% faster
Median TTFT
1.10s
42% faster
Throughput/Dollar
4296
tok/s per $/1M
Speed Comparison
gpt-oss-20B (low)
264 tok/s+1%
Gemini 2.5 Flash-Lite (Reasoning)
270 tok/s+3%
Sarvam 30B (high)
244 tok/s-7%
Benchmarks
MMLU-Pro
53.1%
GPQA Diamond
35.8%
HLE
4.7%
LiveCodeBench
14.0%
SciCode
9.4%
TerminalBench Hard
1.5%
MATH-500
70.3%
AIME
8.0%
AIME 2025
6.0%
IFBench
29.4%
Long Context Recall
9.7%
Tau2
14.0%
Market AverageTop Score