Skip to content

fix(voyage): add voyage-4 embedding models to model cost map #32987

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
devin-ai-integration wants to merge 2 commits into from
Closed

fix(voyage): add voyage-4 embedding models to model cost map #32987

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
eaa10df
fix(voyage): add voyage-4 embedding models to model cost map
devin-ai-integration[bot] Jul 12, 2026
3ba7406
fix(voyage): keep backup diff minimal to voyage-4 entries
devin-ai-integration[bot] Jul 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 24 additions & 0 deletions litellm/model_prices_and_context_window_backup.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37762,6 +37762,30 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-4": {
"input_cost_per_token": 6e-08,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-4-large": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-4-lite": {
"input_cost_per_token": 2e-08,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-code-2": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",
Expand Down
24 changes: 24 additions & 0 deletions model_prices_and_context_window.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37964,6 +37964,30 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-4": {
"input_cost_per_token": 6e-08,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-4-large": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-4-lite": {
"input_cost_per_token": 2e-08,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"voyage/voyage-code-2": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",
Expand Down
53 changes: 53 additions & 0 deletions tests/test_litellm/test_voyage_4_model_metadata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
import json
from pathlib import Path

import pytest

import litellm

VOYAGE_4_MODELS = {
"voyage/voyage-4-large": 1.2e-07,
"voyage/voyage-4": 6e-08,
"voyage/voyage-4-lite": 2e-08,
}


@pytest.mark.parametrize("model,input_cost", VOYAGE_4_MODELS.items())
def test_voyage_4_model_info(model, input_cost):
json_path = Path(__file__).parents[2] / "model_prices_and_context_window.json"
with open(json_path) as f:
model_cost = json.load(f)

info = model_cost.get(model)
assert info is not None, f"{model} not found in model_prices_and_context_window.json"

assert info["litellm_provider"] == "voyage"
assert info["mode"] == "embedding"
assert info["input_cost_per_token"] == input_cost
assert info["output_cost_per_token"] == 0.0
assert info["max_input_tokens"] == 32000
assert info["max_tokens"] == 32000


@pytest.mark.parametrize("model,input_cost", VOYAGE_4_MODELS.items())
def test_voyage_4_get_model_info_surfaces_mode(model, input_cost):
litellm.model_cost = litellm.get_model_cost_map(url="")
info = litellm.get_model_info(model=model)
assert info["mode"] == "embedding"
assert info["input_cost_per_token"] == input_cost
Comment on lines +34 to +37

@greptile-apps greptile-apps Bot Jul 12, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Unguarded global state mutation

litellm.model_cost is a module-level singleton; assigning to it here and never restoring it means any test that runs after this one in the same pytest worker will see the modified value. If, for example, the module-level cost map was already populated from the remote URL before this test ran, subsequent tests that rely on the original value could produce wrong results or false-positive passes. Use a monkeypatch fixture (or @pytest.fixture(autouse=True)) to scope the override to this test only.

Comment on lines +32 to +37

@greptile-apps greptile-apps Bot Jul 12, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Passing url="" to get_model_cost_map relies on an empty-string URL causing httpx to raise an exception, which then triggers the local-fallback path. This is an indirect side-effect of error handling rather than an intentional API contract, and it could silently break if httpx changes its URL-validation behaviour. Setting LITELLM_LOCAL_MODEL_COST_MAP=True via monkeypatch.setenv is the documented, supported way to force the local backup without any network-call attempt.

Suggested change
@pytest.mark.parametrize("model,input_cost", VOYAGE_4_MODELS.items())
def test_voyage_4_get_model_info_surfaces_mode(model, input_cost):
litellm.model_cost = litellm.get_model_cost_map(url="")
info = litellm.get_model_info(model=model)
assert info["mode"] == "embedding"
assert info["input_cost_per_token"] == input_cost
@pytest.mark.parametrize("model,input_cost", VOYAGE_4_MODELS.items())
def test_voyage_4_get_model_info_surfaces_mode(model, input_cost, monkeypatch):
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
info = litellm.get_model_info(model=model)
assert info["mode"] == "embedding"
assert info["input_cost_per_token"] == input_cost

Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!



@pytest.mark.parametrize("model", VOYAGE_4_MODELS.keys())
def test_voyage_4_backup_matches_main(model):
repo_root = Path(__file__).parents[2]
main_path = repo_root / "model_prices_and_context_window.json"
backup_path = repo_root / "litellm" / "model_prices_and_context_window_backup.json"

with open(main_path) as f:
main_cost = json.load(f)
with open(backup_path) as f:
backup_cost = json.load(f)

assert backup_cost.get(model) == main_cost.get(model), (
f"{model} differs between main and backup model cost maps"
)
Loading