scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-12 23:01:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 182

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

Browse source
This commit is contained in:
Devin AI 2026-07-12 03:05:21 +00:00
parent c136797805
commit eaa10df113
3 changed files with 384 additions and 50 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

357
litellm/model_prices_and_context_window_backup.json
View file

@ -17293,6 +17293,46 @@
"tpm": 8000000,
"supports_image_size": false
},
"gemini-3-pro-image": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query"
},
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -17333,6 +17373,44 @@
},
"web_search_billing_unit": "per_query"
},
"gemini-3.1-flash-image": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query"
},
"gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
@ -18747,6 +18825,48 @@
},
"supports_image_size": false
},
"gemini/gemini-3-pro-image": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"rpm": 1000,
"tpm": 4000000,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -18789,6 +18909,47 @@
},
"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,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"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,
"rpm": 1000,
"tpm": 4000000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-image-preview": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
@ -20073,8 +20234,7 @@
"max_tokens": 16000,
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/messages"
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -20087,8 +20247,7 @@
"max_tokens": 16000,
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/messages"
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -20140,8 +20299,7 @@
"max_tokens": 16000,
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/messages"
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -23430,7 +23588,7 @@
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23476,7 +23634,7 @@
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23520,7 +23678,7 @@
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_batches": 1e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23563,7 +23721,7 @@
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_batches": 1e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -23603,9 +23761,9 @@
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 272000,
"max_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00012,
"output_cost_per_token_batches": 6e-05,
@ -23639,9 +23797,9 @@
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 272000,
"max_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00012,
"output_cost_per_token_batches": 6e-05,
@ -31002,6 +31160,22 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/z-ai/glm-5.1": {
"input_cost_per_token": 1.05e-06,
"output_cost_per_token": 3.5e-06,
"cache_read_input_token_cost": 5.25e-07,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "openrouter",
"max_input_tokens": 202752,
"max_output_tokens": 65535,
"max_tokens": 65535,
"mode": "chat",
"source": "https://openrouter.ai/z-ai/glm-5.1",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/minimax/minimax-m2.1": {
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 1.2e-06,
@ -36786,6 +36960,21 @@
"tpm": 8000000,
"supports_image_size": false
},
"vertex_ai/gemini-3-pro-image": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
},
"vertex_ai/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -36801,6 +36990,19 @@
"output_cost_per_token_batches": 6e-06,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
},
"vertex_ai/gemini-3.1-flash-image": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},
"vertex_ai/gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
@ -37762,6 +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",
@ -39089,6 +39315,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.1": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-code": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 3e-07,
@ -39119,6 +39360,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.7-flash": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 0,
"input_cost_per_token": 0,
"output_cost_per_token": 0,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.6": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1.1e-07,
@ -44440,6 +44696,7 @@
"supports_response_schema": true
},
"snowflake/claude-sonnet-4-6": {
"supports_adaptive_thinking": true,
"max_tokens": 16384,
"max_input_tokens": 200000,
"max_output_tokens": 16384,
@ -44858,40 +45115,6 @@
"supports_tool_choice": true,
"supports_vision": false
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.65e-07,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"darkbloom/gpt-oss-20b": {
"input_cost_per_token": 1.45e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7e-08,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"deepseek/deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 3.625e-09,
@ -45047,6 +45270,40 @@
"supports_reasoning": false,
"source": "https://pinstripes.io/pricing"
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.65e-07,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"darkbloom/gpt-oss-20b": {
"input_cost_per_token": 1.45e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7e-08,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"fallback_generalizations": {
"rules": [
{

24
model_prices_and_context_window.json
View file

@ -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",

53
tests/test_litellm/test_voyage_4_model_metadata.py Normal file
View file

@ -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
@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"
)