scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 90

feat: add pricing entry for openrouter/google/gemini-3.1-flash-lite (#28280)

Browse source 
Squash-merged by litellm-agent from ro31337's PR.
This commit is contained in:
Roman Pushkin 2026-05-19 14:16:00 -07:00 • committed by GitHub
parent d9af172d27
commit 87a55f505f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 135 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

52
litellm/model_prices_and_context_window_backup.json
View file

@ -26951,6 +26951,58 @@
"supports_web_search": true,
"tpm": 800000
},
"openrouter/google/gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_per_audio_token": 5e-08,
"input_cost_per_audio_token": 5e-07,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "openrouter",
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
"max_images_per_prompt": 3000,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_pdf_size_mb": 30,
"max_tokens": 65536,
"max_video_length": 1,
"max_videos_per_prompt": 10,
"mode": "chat",
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"rpm": 2000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_audio_output": false,
"supports_code_execution": true,
"supports_file_search": 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,
"tpm": 800000
},
"openrouter/google/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,

52
model_prices_and_context_window.json
View file

@ -27121,6 +27121,58 @@
"supports_web_search": true,
"tpm": 800000
},
"openrouter/google/gemini-3.1-flash-lite": {
"cache_read_input_token_cost": 2.5e-08,
"cache_read_input_token_cost_per_audio_token": 5e-08,
"input_cost_per_audio_token": 5e-07,
"input_cost_per_token": 2.5e-07,
"litellm_provider": "openrouter",
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
"max_images_per_prompt": 3000,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_pdf_size_mb": 30,
"max_tokens": 65536,
"max_video_length": 1,
"max_videos_per_prompt": 10,
"mode": "chat",
"output_cost_per_reasoning_token": 1.5e-06,
"output_cost_per_token": 1.5e-06,
"rpm": 2000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_audio_output": false,
"supports_code_execution": true,
"supports_file_search": 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,
"tpm": 800000
},
"openrouter/google/gemini-3.1-pro-preview": {
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_200k_tokens": 4e-07,

31
tests/test_litellm/test_cost_calculator.py
View file

@ -2371,3 +2371,34 @@ def test_custom_pricing_without_cache_keys_preserves_legacy_behavior():
expected = 1000 * 0.0000025 + 100 * 0.000015
assert cost == pytest.approx(expected)
def test_openrouter_gemini_3_1_flash_lite_stable_pricing():
"""
Test that openrouter/google/gemini-3.1-flash-lite (stable, no -preview suffix)
has a pricing entry.
Google promoted gemini-3.1-flash-lite to GA on 2026-05-07. PR #27933 added the
stable pricing for the bare, gemini/, and vertex_ai/ prefixes but missed the
openrouter/google/ variant — every other Gemini family in the file has an
openrouter/google/ sibling (2.0-flash-001, 2.5-flash, 2.5-pro, 3-flash-preview,
3-pro-preview, 3.1-flash-lite-preview, 3.1-pro-preview), so the gap is a
consistency issue, not a design choice. Same shape as the preview-variant gap
fixed in PR #25610.
Pricing matches the existing -preview entry one-for-one (input $0.25/M, output
$1.50/M, cache-read $0.025/M) — Google did not change costs at the GA cutover.
"""
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
model_name = "openrouter/google/gemini-3.1-flash-lite"
model_info = litellm.model_cost.get(model_name)
assert model_info is not None, f"Missing model pricing entry: {model_name}"
assert model_info["litellm_provider"] == "openrouter"
assert model_info["input_cost_per_token"] == 2.5e-07
assert model_info["output_cost_per_token"] == 1.5e-06
assert model_info["cache_read_input_token_cost"] == 2.5e-08
assert model_info["max_input_tokens"] == 1048576
assert model_info["max_output_tokens"] == 65536