About
Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of [Mistral Large 2](/mistralai/mistral-large-2411). The model is able to understand documents, charts and natural images. The model is...
Related Models
Pricing
Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Blended
$3.00
per 1M tokens
Cheaper than 20% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$3.00
Monthly
$90.00
vs. Similar Models
Olmo 3.1 32B ThinkQ:0.0
$0.24-92%
Ring-flash-2.0Q:+0.1
$0.25-92%
GPT-5 nano (minimal)Q:-0.1
$0.14-95%
OpenAI: GPT-4 TurboQ:-0.2
$15.00+400%
Performance
56
tokens/sec
Faster than 25% of models
0.84
seconds
Faster than 65% of models
0.84
seconds
Faster than 75% of models
Market Median
94 tok/s
41% slower
Median TTFT
1.10s
24% faster
Throughput/Dollar
19
tok/s per $/1M
Speed Comparison
Qwen2.5 Instruct 72B
56 tok/s-0%
Mistral Large 3
56 tok/s-0%
Qwen3.5 Omni Plus
55 tok/s-1%
Context Window
131K
tokens
Larger than 27% of models
Benchmarks
MMLU-Pro
70.1%
GPQA Diamond
50.5%
HLE
3.6%
LiveCodeBench
26.1%
SciCode
29.2%
TerminalBench HardNot evaluated
MATH-500
71.4%
AIME
7.0%
AIME 2025
2.3%
IFBench
34.5%
Long Context Recall
10.3%
Tau2
36.5%
Market AverageTop Score