tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-21 00:24:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(gemini): add gemini-3.1-flash-live-preview to model cost map

Browse Source 
Made-with: Cursor
This commit is contained in:
Sameer Kankute
2026-03-27 11:04:29 +05:30
parent b20cff8673
commit 06c8476544
3 changed files with 131 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+58
View File
@@ -36830,6 +36830,34 @@
"supports_audio_input": true,
"supports_audio_output": true
},
"gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/models",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true
},
"gemini/gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
@@ -36908,6 +36936,36 @@
"tpm": 250000,
"rpm": 10
},
"gemini/gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/models",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"tpm": 250000,
"rpm": 10
},
"gemini-2.5-flash-preview-tts": {
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
model_prices_and_context_window.json
+58
View File
@@ -36830,6 +36830,34 @@
"supports_audio_input": true,
"supports_audio_output": true
},
"gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/models",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true
},
"gemini/gemini-2.5-flash-native-audio-latest": {
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
@@ -36908,6 +36936,36 @@
"tpm": 250000,
"rpm": 10
},
"gemini/gemini-3.1-flash-live-preview": {
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 2.5e-06,
"source": "https://ai.google.dev/gemini-api/docs/models",
"supported_endpoints": [
"/v1/realtime"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text",
"audio"
],
"supports_audio_input": true,
"supports_audio_output": true,
"supports_function_calling": true,
"supports_vision": true,
"tpm": 250000,
"rpm": 10
},
"gemini-2.5-flash-preview-tts": {
"input_cost_per_token": 3e-07,
"litellm_provider": "gemini",
tests/test_litellm/llms/gemini/realtime/test_gemini_realtime_transformation.py
+15
View File
@@ -10,6 +10,7 @@ sys.path.insert(
0, os.path.abspath("../../../../..")
) # Adds the parent directory to the system path
import litellm
from litellm.llms.gemini.realtime.transformation import GeminiRealtimeConfig
from litellm.types.llms.openai import OpenAIRealtimeStreamSessionEvents
@@ -227,3 +228,17 @@ def test_gemini_realtime_transformation_generation_complete():
contains_audio_delta = True
break
assert contains_audio_delta, "Expected audio delta event"
def test_gemini_3_1_flash_live_preview_model_cost_map_entry():
for key in (
"gemini-3.1-flash-live-preview",
"gemini/gemini-3.1-flash-live-preview",
):
assert key in litellm.model_cost
info = litellm.model_cost[key]
assert "/v1/realtime" in info.get("supported_endpoints", [])
assert info.get("max_input_tokens") == 131072
assert info.get("max_output_tokens") == 65536
assert "video" in info.get("supported_modalities", [])
assert info.get("supports_function_calling") is True