Related Models
Pricing
Input
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Blended
$0.17
per 1M tokens
Cheaper than 72% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.17
Monthly
$5.25
vs. Similar Models
OpenAI: GPT-5.2-CodexQ:0.0
$4.81+2650%
Z.ai: GLM 5.1Q:+0.1
$1.50+760%
OpenAI: GPT-5.4 MiniQ:-0.1
$1.69+864%
Qwen3.6 Max PreviewQ:-0.1
$2.92+1571%
Performance
86
tokens/sec
Faster than 45% of models
1.56
seconds
Faster than 33% of models
24.74
seconds
Faster than 20% of models
Market Median
95 tok/s
9% slower
Median TTFT
1.11s
41% slower
Throughput/Dollar
493
tok/s per $/1M
Speed Comparison
Llama 3.2 Instruct 1B
86 tok/s-0%
Ring-flash-2.0
86 tok/s+0%
Reka Flash (Sep '24)
86 tok/s-0%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
84.9%
HLE
25.2%
LiveCodeBenchNot evaluated
SciCode
43.1%
TerminalBench Hard
41.7%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
67.1%
Long Context Recall
62.7%
Tau2
90.6%
Market AverageTop Score