scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-22 05:24:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49

feat(pricing): add Gemini 3.1 Flash Lite Image model pricing

Browse source
This commit is contained in:
Devin AI 2026-07-09 18:10:27 +00:00
parent 131aa050bb
commit ffce258a7a
3 changed files with 232 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

92
litellm/model_prices_and_context_window_backup.json
View file

@ -16804,6 +16804,44 @@
},
"web_search_billing_unit": "per_query"
},
"gemini-3.1-flash-lite-image": {
"input_cost_per_image": 0.00028,
"input_cost_per_token": 2.5e-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": 0.0336,
"output_cost_per_image_token": 3e-05,
"output_cost_per_token": 1.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-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-3.1-flash-lite-preview": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_audio_token": 5e-07,
@ -18263,6 +18301,47 @@
},
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-lite-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": 0.0336,
"output_cost_per_image_token": 3e-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-lite-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/deep-research-pro-preview-12-2025": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -35999,6 +36078,19 @@
"output_cost_per_token": 3e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},
"vertex_ai/gemini-3.1-flash-lite-image": {
"input_cost_per_image": 0.00028,
"input_cost_per_token": 2.5e-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": 0.0336,
"output_cost_per_image_token": 3e-05,
"output_cost_per_token": 1.5e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},
"vertex_ai/gemini-3.1-flash-lite-preview": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_audio_token": 5e-07,

92
model_prices_and_context_window.json
View file

@ -16882,6 +16882,44 @@
},
"web_search_billing_unit": "per_query"
},
"gemini-3.1-flash-lite-image": {
"input_cost_per_image": 0.00028,
"input_cost_per_token": 2.5e-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": 0.0336,
"output_cost_per_image_token": 3e-05,
"output_cost_per_token": 1.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite-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-3.1-flash-lite-preview": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_audio_token": 5e-07,
@ -18424,6 +18462,47 @@
},
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-lite-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": 0.0336,
"output_cost_per_image_token": 3e-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-lite-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/deep-research-pro-preview-12-2025": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -36201,6 +36280,19 @@
"output_cost_per_token": 3e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},
"vertex_ai/gemini-3.1-flash-lite-image": {
"input_cost_per_image": 0.00028,
"input_cost_per_token": 2.5e-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": 0.0336,
"output_cost_per_image_token": 3e-05,
"output_cost_per_token": 1.5e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},
"vertex_ai/gemini-3.1-flash-lite-preview": {
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_audio_token": 5e-07,

48
tests/test_litellm/llms/gemini/test_cost_calculator.py
View file

@ -301,3 +301,51 @@ def test_gemini_image_generation_cost_no_web_search_when_absent():
)
assert cost_zero == cost_none
def test_gemini_3_1_flash_lite_image_pricing_metadata():
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
model_info = litellm.get_model_info(
model="gemini/gemini-3.1-flash-lite-image",
custom_llm_provider="gemini",
)
assert model_info["mode"] == "image_generation"
assert model_info["input_cost_per_token"] == pytest.approx(2.5e-07)
assert model_info["output_cost_per_token"] == pytest.approx(1.5e-06)
assert model_info["output_cost_per_image_token"] == pytest.approx(3e-05)
assert model_info["output_cost_per_image"] == pytest.approx(0.0336)
def test_gemini_3_1_flash_lite_image_generation_cost():
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
model = "gemini/gemini-3.1-flash-lite-image"
model_info = litellm.get_model_info(model=model, custom_llm_provider="gemini")
input_text_tokens = 20
output_image_tokens = 1120
image_response = ImageResponse(
data=[ImageObject(b64_json="img1")],
usage=ImageUsage(
input_tokens=input_text_tokens,
input_tokens_details=ImageUsageInputTokensDetails(
text_tokens=input_text_tokens,
image_tokens=0,
),
output_tokens=output_image_tokens,
total_tokens=input_text_tokens + output_image_tokens,
),
)
cost = gemini_image_generation_cost_calculator(
model=model,
image_response=image_response,
)
expected_cost = (
input_text_tokens * model_info["input_cost_per_token"]
+ output_image_tokens * model_info["output_cost_per_image_token"]
)
assert round(cost, 10) == round(expected_cost, 10)