Related Models
Pricing
Input
$0.75
per 1M tokens
Output
$4.50
per 1M tokens
Blended
$1.69
per 1M tokens
Cheaper than 26% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.69
Monthly
$50.64
vs. Similar Models
Mistral: Mistral Medium 3.5Q:+0.1
$3.00+78%
StepFun: Step 3.7 FlashQ:-0.1
$0.44-74%
Claude 4.5 Haiku (Reasoning)Q:-0.2
$2.00+18%
GPT-5.4 nano (medium)Q:+0.4
$0.46-73%
Performance
175
tokens/sec
Faster than 82% of models
5.38
seconds
Faster than 16% of models
5.38
seconds
Faster than 47% of models
Market Median
94 tok/s
87% faster
Median TTFT
1.10s
387% slower
Throughput/Dollar
104
tok/s per $/1M
Speed Comparison
Llama 3.1 Instruct 8B
173 tok/s-1%
Qwen3 30B A3B 2507 Instruct
173 tok/s-1%
OpenAI: GPT-5 Codex
177 tok/s+1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
82.3%
HLE
17.1%
LiveCodeBenchNot evaluated
SciCode
44.2%
TerminalBench Hard
34.1%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
64.8%
Long Context Recall
61.3%
Tau2
36.5%
Market AverageTop Score