Related Models
Pricing
Input
$2.50
per 1M tokens
Output
$15.00
per 1M tokens
Blended
$5.63
per 1M tokens
Cheaper than 11% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$5.63
Monthly
$168.75
vs. Similar Models
DeepSeek: DeepSeek V4 FlashQ:-0.2
$0.11-98%
MiMo-V2-ProQ:-0.2
$1.50-73%
Claude Opus 4.5 (Reasoning)Q:+0.3
$10.00+78%
DeepSeek V4 Pro (Reasoning, High Effort)Q:+0.3
$0.54-90%
Performance
132
tokens/sec
Faster than 68% of models
1.13
seconds
Faster than 50% of models
1.13
seconds
Faster than 65% of models
Market Median
93 tok/s
42% faster
Median TTFT
1.14s
1% faster
Throughput/Dollar
23
tok/s per $/1M
Speed Comparison
Qwen3 VL 8B (Reasoning)
132 tok/s-0%
GPT-5.6 Terra (Non-reasoning)
132 tok/s+0%
IBM: Granite 4.1 8B
131 tok/s-1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
84.3%
HLE
27.4%
LiveCodeBenchNot evaluated
SciCode
49.2%
TerminalBench Hard
43.9%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
59.7%
Long Context Recall
64.3%
Tau2
60.5%
Market AverageTop Score