If you want to only subset several samples, try:

bcftools view combined.vcf.gz -s sample_ID -Oz > sample_ID.vcf.gz

If you want to subset every sample, try:

bcftools +split input.vcf.gz -Oz -o vcf_per_sample

Here's a Python API solution using the pyvcf submodule I wrote:

>>> from fuc import pyvcf
>>> data = {
...     'CHROM': ['chr1', 'chr1'],
...     'POS': [100, 101],
...     'ID': ['.', '.'],
...     'REF': ['G', 'T'],
...     'ALT': ['A', 'C'],
...     'QUAL': ['.', '.'],
...     'FILTER': ['.', '.'],
...     'INFO': ['.', '.'],
...     'FORMAT': ['GT:DP', 'GT:DP'],
...     'A': ['0/1:30', '0/1:29'],
...     'B': ['0/1:24', '0/1:30'],
...     'C': ['0/1:18', '0/1:24'],
... }
>>> vf = pyvcf.VcfFrame.from_dict([], data)
>>> # vf = pyvcf.VcfFrame.from_file('in.vcf')
>>> vf.df
  CHROM  POS ID REF ALT QUAL FILTER INFO FORMAT       A       B       C
0  chr1  100  .   G   A    .      .    .  GT:DP  0/1:30  0/1:24  0/1:18
1  chr1  101  .   T   C    .      .    .  GT:DP  0/1:29  0/1:30  0/1:24
>>> a_vf = vf.subset('A')
>>> a_vf.df
  CHROM  POS ID REF ALT QUAL FILTER INFO FORMAT       A
0  chr1  100  .   G   A    .      .    .  GT:DP  0/1:30
1  chr1  101  .   T   C    .      .    .  GT:DP  0/1:29
>>> a_vf.to_file('A.vcf')