Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.20
per 1M tokens
Blended
$0.20
per 1M tokens
Cheaper than 69% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.20
Monthly
$6.00
vs. Similar Models
Qwen: Qwen3 VL 32B InstructQ:0.0
$0.18-9%
OpenAI: GPT-4oQ:+0.1
$4.38+2087%
DeepSeek R1 Distill Qwen 32BQ:-0.1
$0.29+45%
Z.ai: GLM 4.6VQ:-0.1
$0.45+125%
Performance
86
tokens/sec
Faster than 46% of models
0.49
seconds
Faster than 88% of models
0.49
seconds
Faster than 92% of models
Market Median
94 tok/s
9% slower
Median TTFT
1.11s
56% faster
Throughput/Dollar
430
tok/s per $/1M
Speed Comparison
Reka Flash (Sep '24)
86 tok/s+0%
Llama 3.2 Instruct 1B
86 tok/s-0%
MiMo-V2.5
86 tok/s+0%
Benchmarks
MMLU-Pro
69.3%
GPQA Diamond
57.2%
HLE
4.6%
LiveCodeBench
35.1%
SciCode
23.6%
TerminalBench Hard
4.5%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025
30.0%
IFBench
32.0%
Long Context Recall
22.0%
Tau2
27.2%
Market AverageTop Score