scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36

Merge pull request #37473 from BerriAI/litellm_model_registry_audit_20260819

Browse source 
fix(model_prices): correct gemini 3.1 flash image and deepseek v4 pricing, add openai deprecation dates
This commit is contained in:
Mateo Wang 2026-08-19 14:50:49 -07:00 • committed by GitHub
commit b8d5139701
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 58 additions and 58 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
litellm/model_prices_and_context_window_backup.json
View file

@ -20689,8 +20689,8 @@
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-image": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -20698,8 +20698,8 @@
"mode": "image_generation",
"output_cost_per_image": 0.045,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"rpm": 1000,
"tpm": 4000000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image",
@ -20732,8 +20732,8 @@
},
"gemini/gemini-3.1-flash-image-preview": {
"deprecation_date": "2026-06-25",
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -20741,8 +20741,8 @@
"mode": "image_generation",
"output_cost_per_image": 0.045,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"rpm": 1000,
"tpm": 4000000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview",
@ -48180,15 +48180,15 @@
},
"deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 2.8e-09,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token_cache_hit": 2.8e-09,
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 4.4e-07,
"input_cost_per_token_cache_hit": 1.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 1.32e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@ -48206,15 +48206,15 @@
},
"deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 3.625e-09,
"input_cost_per_token": 4.35e-07,
"input_cost_per_token_cache_hit": 3.625e-09,
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 8.7e-07,
"output_cost_per_token": 3.96e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@ -48232,15 +48232,15 @@
},
"deepseek/deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 2.8e-09,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token_cache_hit": 2.8e-09,
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 4.4e-07,
"input_cost_per_token_cache_hit": 1.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 1.32e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@ -48258,15 +48258,15 @@
},
"deepseek/deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 3.625e-09,
"input_cost_per_token": 4.35e-07,
"input_cost_per_token_cache_hit": 3.625e-09,
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 8.7e-07,
"output_cost_per_token": 3.96e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"

48
model_prices_and_context_window.json
View file

@ -20689,8 +20689,8 @@
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-image": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -20698,8 +20698,8 @@
"mode": "image_generation",
"output_cost_per_image": 0.045,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"rpm": 1000,
"tpm": 4000000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image",
@ -20732,8 +20732,8 @@
},
"gemini/gemini-3.1-flash-image-preview": {
"deprecation_date": "2026-06-25",
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
@ -20741,8 +20741,8 @@
"mode": "image_generation",
"output_cost_per_image": 0.045,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"output_cost_per_token": 3e-06,
"output_cost_per_token_batches": 1.5e-06,
"rpm": 1000,
"tpm": 4000000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview",
@ -48180,15 +48180,15 @@
},
"deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 2.8e-09,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token_cache_hit": 2.8e-09,
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 4.4e-07,
"input_cost_per_token_cache_hit": 1.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 1.32e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@ -48206,15 +48206,15 @@
},
"deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 3.625e-09,
"input_cost_per_token": 4.35e-07,
"input_cost_per_token_cache_hit": 3.625e-09,
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 8.7e-07,
"output_cost_per_token": 3.96e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@ -48232,15 +48232,15 @@
},
"deepseek/deepseek-v4-flash": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 2.8e-09,
"input_cost_per_token": 1.4e-07,
"input_cost_per_token_cache_hit": 2.8e-09,
"cache_read_input_token_cost": 1.4e-08,
"input_cost_per_token": 4.4e-07,
"input_cost_per_token_cache_hit": 1.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 1.32e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"
@ -48258,15 +48258,15 @@
},
"deepseek/deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 3.625e-09,
"input_cost_per_token": 4.35e-07,
"input_cost_per_token_cache_hit": 3.625e-09,
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"input_cost_per_token_cache_hit": 4.4e-08,
"litellm_provider": "deepseek",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"mode": "chat",
"output_cost_per_token": 8.7e-07,
"output_cost_per_token": 3.96e-06,
"source": "https://api-docs.deepseek.com/quick_start/pricing",
"supported_endpoints": [
"/v1/chat/completions"

20
tests/test_litellm/test_utils.py
View file

@ -3787,8 +3787,8 @@ def test_deepseek_v4_models_in_cost_map():
configured in model_prices_and_context_window.json.
Prices sourced from https://api-docs.deepseek.com/quick_start/pricing:
- deepseek-v4-flash: $0.14/M input, $0.28/M output
- deepseek-v4-pro: $0.435/M input, $0.87/M output (75% discounted active price)
- deepseek-v4-flash: $0.44/M input, $1.32/M output
- deepseek-v4-pro: $1.32/M input, $3.96/M output
Closes https://github.com/BerriAI/litellm/issues/26709
"""
@ -3801,8 +3801,8 @@ def test_deepseek_v4_models_in_cost_map():
# --- bare model names ---
for key, expected_input, expected_output, expected_cache in [
("deepseek-v4-flash", 1.4e-07, 2.8e-07, 2.8e-09),
("deepseek-v4-pro", 4.35e-07, 8.7e-07, 3.625e-09),
("deepseek-v4-flash", 4.4e-07, 1.32e-06, 1.4e-08),
("deepseek-v4-pro", 1.32e-06, 3.96e-06, 4.4e-08),
]:
info = model_cost.get(key)
assert info is not None, f"{key} missing from model_prices_and_context_window.json"
@ -3817,8 +3817,8 @@ def test_deepseek_v4_models_in_cost_map():
# --- provider-prefixed names ---
for key, expected_input, expected_output, expected_cache in [
("deepseek/deepseek-v4-flash", 1.4e-07, 2.8e-07, 2.8e-09),
("deepseek/deepseek-v4-pro", 4.35e-07, 8.7e-07, 3.625e-09),
("deepseek/deepseek-v4-flash", 4.4e-07, 1.32e-06, 1.4e-08),
("deepseek/deepseek-v4-pro", 1.32e-06, 3.96e-06, 4.4e-08),
]:
info = model_cost.get(key)
assert info is not None, f"{key} missing from model_prices_and_context_window.json"
@ -3845,8 +3845,8 @@ def test_deepseek_v4_models_in_backup_cost_map():
# --- bare model names ---
for key, expected_input, expected_output, expected_cache in [
("deepseek-v4-flash", 1.4e-07, 2.8e-07, 2.8e-09),
("deepseek-v4-pro", 4.35e-07, 8.7e-07, 3.625e-09),
("deepseek-v4-flash", 4.4e-07, 1.32e-06, 1.4e-08),
("deepseek-v4-pro", 1.32e-06, 3.96e-06, 4.4e-08),
]:
info = model_cost.get(key)
assert info is not None, f"{key} missing from backup JSON"
@ -3859,8 +3859,8 @@ def test_deepseek_v4_models_in_backup_cost_map():
# --- provider-prefixed names ---
for key, expected_input, expected_output, expected_cache in [
("deepseek/deepseek-v4-flash", 1.4e-07, 2.8e-07, 2.8e-09),
("deepseek/deepseek-v4-pro", 4.35e-07, 8.7e-07, 3.625e-09),
("deepseek/deepseek-v4-flash", 4.4e-07, 1.32e-06, 1.4e-08),
("deepseek/deepseek-v4-pro", 1.32e-06, 3.96e-06, 4.4e-08),
]:
info = model_cost.get(key)
assert info is not None, f"{key} missing from backup JSON"