Skip to main content
Back to Explore

Apertus 70B Instruct

Swiss AI Initiative·Released 2025-09-02

Pricing

Input

$0.82

per 1M tokens

Output

$2.92

per 1M tokens

Blended

$1.34

per 1M tokens

Cheaper than 32% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$1.34

Monthly

$40.35

vs. Similar Models

Mixtral 8x7B InstructQ:0.0
$0.51-62%
Jamba 1.6 MiniQ:+0.2
$0.25-81%
Qwen3 1.7B (Reasoning)Q:+0.2
$0.40-70%
Command-R (Mar '24)Q:-0.3
$0.75-44%

Performance

64

tokens/sec

Faster than 33% of models

1.61

seconds

Faster than 32% of models

1.61

seconds

Faster than 56% of models

Market Median

94 tok/s

31% slower

Median TTFT

1.10s

45% slower

Throughput/Dollar

48

tok/s per $/1M

Speed Comparison

Gemma 3n E2B Instruct
64 tok/s-0%
Qwen3 14B (Non-reasoning)
64 tok/s-0%
Qwen3 235B A22B 2507 Instruct
65 tok/s+1%

Benchmarks

MMLU-ProNot evaluated
GPQA Diamond
27.2%
HLE
5.5%
LiveCodeBenchNot evaluated
SciCode
5.7%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
25.9%
Long Context Recall
0.0%
Tau2
12.9%
Market AverageTop Score

Quick Compare

Similar Models

Compare all 7 models