Related Models
Pricing
Input
$0.45
per 1M tokens
Output
$1.80
per 1M tokens
Blended
$0.79
per 1M tokens
Cheaper than 43% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.79
Monthly
$23.61
vs. Similar Models
DeepSeek R1 Distill Qwen 32BQ:+0.1
$0.29-63%
Z.ai: GLM 4.6VQ:+0.1
$0.45-43%
Qwen: Qwen3 VL 32B InstructQ:+0.2
$0.18-77%
Ministral 3 14BQ:+0.2
$0.20-75%
Performance
62
tokens/sec
Faster than 30% of models
1.17
seconds
Faster than 47% of models
1.17
seconds
Faster than 64% of models
Market Median
94 tok/s
34% slower
Median TTFT
1.11s
5% slower
Throughput/Dollar
79
tok/s per $/1M
Speed Comparison
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
63 tok/s+0%
Cohere: Command A
62 tok/s-1%
Qwen3 8B (Non-reasoning)
62 tok/s-1%
Benchmarks
MMLU-Pro
76.2%
GPQA Diamond
61.3%
HLE
4.7%
LiveCodeBench
34.3%
SciCode
29.9%
TerminalBench Hard
6.1%
MATH-500
90.2%
AIME
32.7%
AIME 2025
23.7%
IFBench
36.6%
Long Context Recall
0.0%
Tau2
27.2%
Market AverageTop Score