diff --git a/requirements.txt b/requirements.txt
index 8d7372cfe..ca4099be5 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -35,3 +35,4 @@ mypy==0.910
 types-dataclasses>=0.1.3; python_version < "3.7"
 types-mock>=0.1.1
 types-requests
+black>=22.0,<23.0
diff --git a/spacy/language.py b/spacy/language.py
index fdce34ac4..e8fd2720c 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -131,7 +131,7 @@ class Language:
         self,
         vocab: Union[Vocab, bool] = True,
         *,
-        max_length: int = 10 ** 6,
+        max_length: int = 10**6,
         meta: Dict[str, Any] = {},
         create_tokenizer: Optional[Callable[["Language"], Callable[[str], Doc]]] = None,
         batch_size: int = 1000,
diff --git a/spacy/ml/models/multi_task.py b/spacy/ml/models/multi_task.py
index 9e1face63..a7d67c6dd 100644
--- a/spacy/ml/models/multi_task.py
+++ b/spacy/ml/models/multi_task.py
@@ -85,7 +85,7 @@ def get_characters_loss(ops, docs, prediction, nr_char):
     target = ops.asarray(to_categorical(target_ids, n_classes=256), dtype="f")
     target = target.reshape((-1, 256 * nr_char))
     diff = prediction - target
-    loss = (diff ** 2).sum()
+    loss = (diff**2).sum()
     d_target = diff / float(prediction.shape[0])
     return loss, d_target
 
diff --git a/spacy/pipeline/spancat.py b/spacy/pipeline/spancat.py
index 32c1275a6..5d0d8f17e 100644
--- a/spacy/pipeline/spancat.py
+++ b/spacy/pipeline/spancat.py
@@ -377,7 +377,7 @@ class SpanCategorizer(TrainablePipe):
         # If the prediction is 0.9 and it's false, the gradient will be
         # 0.9 (0.9 - 0.0)
         d_scores = scores - target
-        loss = float((d_scores ** 2).sum())
+        loss = float((d_scores**2).sum())
         return loss, d_scores
 
     def initialize(
diff --git a/spacy/pipeline/textcat.py b/spacy/pipeline/textcat.py
index 30a65ec52..7f5510933 100644
--- a/spacy/pipeline/textcat.py
+++ b/spacy/pipeline/textcat.py
@@ -281,7 +281,7 @@ class TextCategorizer(TrainablePipe):
         bp_scores(gradient)
         if sgd is not None:
             self.finish_update(sgd)
-        losses[self.name] += (gradient ** 2).sum()
+        losses[self.name] += (gradient**2).sum()
         return losses
 
     def _examples_to_truth(
@@ -315,7 +315,7 @@ class TextCategorizer(TrainablePipe):
         not_missing = self.model.ops.asarray(not_missing)  # type: ignore
         d_scores = (scores - truths) / scores.shape[0]
         d_scores *= not_missing
-        mean_square_error = (d_scores ** 2).sum(axis=1).mean()
+        mean_square_error = (d_scores**2).sum(axis=1).mean()
         return float(mean_square_error), d_scores
 
     def add_label(self, label: str) -> int:
diff --git a/spacy/tests/package/test_requirements.py b/spacy/tests/package/test_requirements.py
index 75908df59..e20227455 100644
--- a/spacy/tests/package/test_requirements.py
+++ b/spacy/tests/package/test_requirements.py
@@ -12,6 +12,7 @@ def test_build_dependencies():
         "flake8",
         "hypothesis",
         "pre-commit",
+        "black",
         "mypy",
         "types-dataclasses",
         "types-mock",