Related Models
Pricing
Input
$2.75
per 1M tokens
Output
$8.10
per 1M tokens
Blended
$4.09
per 1M tokens
Cheaper than 15% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$4.09
Monthly
$122.64
vs. Similar Models
GPT-3.5 TurboQ:0.0
$0.75-82%
Mistral Small (Feb '24)Q:0.0
$1.50-63%
Llama 3 Instruct 70BQ:-0.1
$1.18-71%
Gemma 3 12B InstructQ:-0.2
$0.14-97%
Performance
94
tokens/sec
Faster than 50% of models
0.59
seconds
Faster than 78% of models
0.59
seconds
Faster than 85% of models
Market Median
94 tok/s
0% faster
Median TTFT
1.10s
47% faster
Throughput/Dollar
23
tok/s per $/1M
Speed Comparison
Qwen3 32B (Reasoning)
94 tok/s+0%
GPT-5 (low)
94 tok/s-0%
OpenAI: GPT-5.1
94 tok/s-0%
Benchmarks
MMLU-Pro
49.1%
GPQA Diamond
34.9%
HLE
3.4%
LiveCodeBench
9.9%
SciCode
11.8%
TerminalBench HardNot evaluated
MATH-500
40.5%
AIME
3.7%
AIME 2025Not evaluated
IFBenchNot evaluated
Long Context RecallNot evaluated
Tau2Not evaluated
Market AverageTop Score