Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.52
per 1M tokens
Blended
$0.28
per 1M tokens
Cheaper than 63% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.28
Monthly
$8.28
vs. Similar Models
Nova 2.0 Omni (Non-reasoning)Q:0.0
$0.85+208%
Qwen3 VL 8B (Reasoning)Q:+0.1
$0.66+139%
DeepSeek V3 (Dec '24)Q:-0.1
$0.52+89%
Qwen3.5 2BQ:-0.3
$0.04-86%
Performance
94
tokens/sec
Faster than 50% of models
1.21
seconds
Faster than 43% of models
22.58
seconds
Faster than 23% of models
Market Median
94 tok/s
1% slower
Median TTFT
1.11s
9% slower
Throughput/Dollar
339
tok/s per $/1M
Speed Comparison
DeepSeek V4 Flash (Non-reasoning)
94 tok/s+1%
OpenAI: GPT-5.1
95 tok/s+1%
MiMo-V2-Flash (Non-reasoning)
95 tok/s+1%
Benchmarks
MMLU-Pro
79.8%
GPQA Diamond
66.8%
HLE
8.3%
LiveCodeBench
54.6%
SciCode
35.4%
TerminalBench Hard
3.0%
MATH-500
96.1%
AIME
80.7%
AIME 2025
73.0%
IFBench
36.3%
Long Context Recall
0.0%
Tau2
29.8%
Market AverageTop Score