scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-11 08:38:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 280

revert(cost-map): leave mistral-large-4 rows to #48825

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-10-28 12:40:28 +00:00
parent 1639274003
commit 5697399125
3 changed files with 17 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm/model_prices_and_context_window_backup.json
View file

@ -42055,13 +42055,13 @@
"mode": "embedding"
},
"mistral/mistral-large-4": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.36e-06,
"cache_read_input_token_cost": 6.8e-08,
"input_cost_per_token": 6.8e-07,
"litellm_provider": "mistral",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 4.18e-06,
"output_cost_per_token": 2.09e-06,
"reasoning_effort_levels": [
"none",
"high"
@ -42076,13 +42076,13 @@
"supports_vision": true
},
"mistral/mistral-large-4-0": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.36e-06,
"cache_read_input_token_cost": 6.8e-08,
"input_cost_per_token": 6.8e-07,
"litellm_provider": "mistral",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 4.18e-06,
"output_cost_per_token": 2.09e-06,
"reasoning_effort_levels": [
"none",
"high"

12
model_prices_and_context_window.json
View file

@ -42055,13 +42055,13 @@
"mode": "embedding"
},
"mistral/mistral-large-4": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.36e-06,
"cache_read_input_token_cost": 6.8e-08,
"input_cost_per_token": 6.8e-07,
"litellm_provider": "mistral",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 4.18e-06,
"output_cost_per_token": 2.09e-06,
"reasoning_effort_levels": [
"none",
"high"
@ -42076,13 +42076,13 @@
"supports_vision": true
},
"mistral/mistral-large-4-0": {
"cache_read_input_token_cost": 1.4e-07,
"input_cost_per_token": 1.36e-06,
"cache_read_input_token_cost": 6.8e-08,
"input_cost_per_token": 6.8e-07,
"litellm_provider": "mistral",
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"mode": "chat",
"output_cost_per_token": 4.18e-06,
"output_cost_per_token": 2.09e-06,
"reasoning_effort_levels": [
"none",
"high"

12
tests/unit/test_mistral_large_4_model_metadata.py
View file

@ -32,7 +32,9 @@ def test_metadata_and_backup(model):
assert info["litellm_provider"] == "mistral"
assert info["mode"] == "chat"
assert info["max_input_tokens"] == 1048576
assert 0 < info["cache_read_input_token_cost"] < info["input_cost_per_token"] < info["output_cost_per_token"]
assert info["input_cost_per_token"] == 6.8e-07
assert info["output_cost_per_token"] == 2.09e-06
assert info["cache_read_input_token_cost"] == 6.8e-08
assert info["reasoning_effort_levels"] == ["none", "high"]
for capability in (
"supports_vision",
@ -57,16 +59,12 @@ def test_reasoning_effort(model, effort):
@pytest.mark.parametrize("model", MODELS)
def test_completion_cost(model):
info = litellm.get_model_info(model)
input_rate = info["input_cost_per_token"]
output_rate = info["output_cost_per_token"]
cache_read_rate = info["cache_read_input_token_cost"]
uncached_response = litellm.ModelResponse(
model=model.split("/", 1)[1],
usage={"prompt_tokens": 1000, "completion_tokens": 100, "total_tokens": 1100},
)
assert litellm.completion_cost(completion_response=uncached_response, model=model) == pytest.approx(
1000 * input_rate + 100 * output_rate
1000 * 6.8e-07 + 100 * 2.09e-06
)
response = litellm.ModelResponse(
model=model.split("/", 1)[1],
@ -78,7 +76,7 @@ def test_completion_cost(model):
},
)
assert litellm.completion_cost(completion_response=response, model=model) == pytest.approx(
400 * input_rate + 600 * cache_read_rate + 100 * output_rate
400 * 6.8e-07 + 600 * 6.8e-08 + 100 * 2.09e-06
)