Related Models
Pricing
Input
$0.30
per 1M tokens
Output
$2.60
per 1M tokens
Blended
$0.88
per 1M tokens
Cheaper than 39% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.88
Monthly
$26.25
vs. Similar Models
Qwen: Qwen3.5-35B-A3BQ:0.0
$0.35-59%
Claude 4.5 Sonnet (Non-reasoning)Q:0.0
$6.00+586%
Qwen3.6 27B (Non-reasoning)Q:0.0
$1.35+54%
Gemma 4 31B (Reasoning)Q:+0.1
$0.20-77%
Performance
90
tokens/sec
Faster than 48% of models
1.56
seconds
Faster than 33% of models
1.56
seconds
Faster than 57% of models
Market Median
94 tok/s
4% slower
Median TTFT
1.10s
41% slower
Throughput/Dollar
103
tok/s per $/1M
Speed Comparison
Grok 4 Fast (Reasoning)
90 tok/s-0%
MiMo-V2-Flash (Feb 2026)
90 tok/s-0%
Hermes 4 - Llama-3.1 70B (Non-reasoning)
90 tok/s+1%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
84.2%
HLE
13.2%
LiveCodeBenchNot evaluated
SciCode
36.7%
TerminalBench Hard
31.8%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
46.9%
Long Context Recall
55.7%
Tau2
87.1%
Market AverageTop Score