scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

Merge pull request #39340 from BerriAI/litellm_gemini_3_8_flash

Browse source 
feat(gemini): day-0 pricing for gemini-3.8-flash
This commit is contained in:
Mateo Wang 2026-09-02 09:24:24 -07:00 • committed by GitHub
commit 55e9e4ce2f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 430 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

173
litellm/model_prices_and_context_window_backup.json
View file

@ -23514,6 +23514,63 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"vertex_ai/gemini-3.8-flash": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"regional_endpoint_uplift_multiplier": 1.1,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"vertex_ai/gemini-3.1-pro-preview": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 2e-07,
@ -25351,6 +25408,65 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-3.8-flash": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 2000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 800000,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-omni-flash-preview": {
"input_cost_per_audio_token": 1.5e-06,
"input_cost_per_token": 1.5e-06,
@ -25759,6 +25875,63 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-3.8-flash": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-2.5-pro-preview-tts": {
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_audio_token": 7e-07,

173
model_prices_and_context_window.json
View file

@ -23514,6 +23514,63 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"vertex_ai/gemini-3.8-flash": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"regional_endpoint_uplift_multiplier": 1.1,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"vertex_ai/gemini-3.1-pro-preview": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 2e-07,
@ -25351,6 +25408,65 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-3.8-flash": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 2000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 800000,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-omni-flash-preview": {
"input_cost_per_audio_token": 1.5e-06,
"input_cost_per_token": 1.5e-06,
@ -25759,6 +25875,63 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-3.8-flash": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-2.5-pro-preview-tts": {
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_audio_token": 7e-07,

80
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -4200,6 +4200,86 @@ def test_generic_cost_per_token_gemini_37_flash(_local_model_cost_map):
assert completion_cost == pytest.approx(0.001875)
GEMINI_38_FLASH_LAUNCH_PRICING = [
("gemini-3.8-flash", 7.5e-07, 3.75e-06, 7.5e-08),
("gemini/gemini-3.8-flash", 7.5e-07, 3.75e-06, 7.5e-08),
("vertex_ai/gemini-3.8-flash", 7.5e-07, 3.75e-06, 7.5e-08),
]
@pytest.mark.parametrize("model,input_cost,output_cost,cache_read_cost", GEMINI_38_FLASH_LAUNCH_PRICING)
def test_gemini_38_flash_launch_pricing(model, input_cost, output_cost, cache_read_cost, _local_model_cost_map):
model_cost_map = litellm.model_cost[model]
assert model_cost_map["input_cost_per_token"] == input_cost
assert model_cost_map["output_cost_per_token"] == output_cost
assert model_cost_map["output_cost_per_reasoning_token"] == output_cost
assert model_cost_map["cache_read_input_token_cost"] == cache_read_cost
assert model_cost_map["mode"] == "chat"
assert model_cost_map["supports_reasoning"] is True
assert model_cost_map["supports_function_calling"] is True
assert model_cost_map["max_input_tokens"] == 1048576
GEMINI_38_FLASH_FIELDS_SHARED_WITH_37_FLASH = (
"input_cost_per_token",
"output_cost_per_token",
"output_cost_per_reasoning_token",
"cache_read_input_token_cost",
"input_cost_per_token_batches",
"output_cost_per_token_batches",
"input_cost_per_token_flex",
"output_cost_per_token_flex",
"cache_read_input_token_cost_flex",
"input_cost_per_token_priority",
"output_cost_per_token_priority",
"cache_read_input_token_cost_priority",
"search_context_cost_per_query",
"google_maps_grounding_cost_per_query",
"prompt_cache_min_tokens",
"max_input_tokens",
"max_output_tokens",
"supports_reasoning",
"supports_function_calling",
"supports_prompt_caching",
"supports_vision",
"supports_pdf_input",
"supports_audio_input",
"supports_video_input",
"supports_response_schema",
"supports_tool_choice",
"supports_web_search",
"supports_url_context",
)
@pytest.mark.parametrize("prefix", ["", "gemini/", "vertex_ai/"])
def test_gemini_38_flash_matches_37_flash_promotional_pricing(prefix, _local_model_cost_map):
new_model = litellm.model_cost[f"{prefix}gemini-3.8-flash"]
old_model = litellm.model_cost[f"{prefix}gemini-3.7-flash"]
for field in GEMINI_38_FLASH_FIELDS_SHARED_WITH_37_FLASH:
assert new_model[field] == old_model[field], field
def test_generic_cost_per_token_gemini_38_flash(_local_model_cost_map):
usage = Usage(
prompt_tokens=1000,
completion_tokens=500,
total_tokens=1500,
completion_tokens_details=CompletionTokensDetailsWrapper(
reasoning_tokens=200,
text_tokens=300,
),
prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=1000),
)
prompt_cost, completion_cost = generic_cost_per_token(
model="gemini-3.8-flash",
usage=usage,
custom_llm_provider="gemini",
)
assert prompt_cost == pytest.approx(0.00075)
assert completion_cost == pytest.approx(0.001875)
def test_grok_46_launch_pricing(_local_model_cost_map):
model_cost_map = litellm.model_cost["xai/grok-4.6"]
assert model_cost_map["input_cost_per_token"] == 2e-06

3
tests/test_litellm/llms/vertex_ai/gemini/test_vertex_ai_gemini_transformation.py
View file

@ -1096,10 +1096,13 @@ def test_natively_signed_parallel_turn_never_carries_a_placeholder(model):
"gemini-3.5-flash",
"gemini-3.6-flash",
"gemini-3.7-flash",
"gemini-3.8-flash",
"vertex_ai/gemini-3.5-flash",
"vertex_ai/gemini-3.7-flash",
"vertex_ai/gemini-3.8-flash",
"gemini/gemini-3.5-flash",
"gemini/gemini-3.7-flash",
"gemini/gemini-3.8-flash",
],
)
def test_placeholder_scoped_to_first_call_across_gemini_3_variants(model):

1
tests/test_litellm/test_utils.py
View file

@ -4655,6 +4655,7 @@ GEMINI_4096_CACHE_MIN_MODELS: Final = tuple(
"gemini-3.5-flash",
"gemini-3.6-flash",
"gemini-3.7-flash",
"gemini-3.8-flash",
"gemini-3.1-pro-preview",
"gemini-3.1-pro-preview-customtools",
)