Related Models
Pricing
Input
$0.11
per 1M tokens
Output
$1.26
per 1M tokens
Blended
$0.40
per 1M tokens
Cheaper than 56% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.40
Monthly
$11.94
vs. Similar Models
Jamba 1.6 MiniQ:0.0
$0.25-37%
Jamba 1.5 MiniQ:+0.1
$0.25-37%
Olmo 3 7B InstructQ:+0.2
$0.13-69%
Apertus 70B InstructQ:-0.2
$1.34+238%
Performance
138
tokens/sec
Faster than 68% of models
0.91
seconds
Faster than 61% of models
15.46
seconds
Faster than 32% of models
Market Median
94 tok/s
47% faster
Median TTFT
1.10s
17% faster
Throughput/Dollar
346
tok/s per $/1M
Speed Comparison
Qwen3 1.7B (Non-reasoning)
138 tok/s+1%
OpenAI: GPT-5.2-Codex
138 tok/s+1%
OpenAI: o1
140 tok/s+2%
Benchmarks
MMLU-Pro
57.0%
GPQA Diamond
35.6%
HLE
4.8%
LiveCodeBench
30.8%
SciCode
4.3%
TerminalBench Hard
0.0%
MATH-500
89.4%
AIME
51.0%
AIME 2025
38.7%
IFBench
26.9%
Long Context Recall
0.0%
Tau2
26.0%
Market AverageTop Score