scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-26 01:12:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 98

feat(gemini): add gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts prices (#42752)

Browse source 
* feat(gemini): add gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts prices

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(gemini): bill tiered TTS output through output_cost_per_token tiers

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-09-23 09:28:09 -07:00 • committed by GitHub
parent cddc53464e
commit 21530d887b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 98 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

48
litellm/model_prices_and_context_window_backup.json
View file

@ -55199,6 +55199,54 @@
"supports_response_schema": false,
"supports_web_search": false
},
"gemini/gemini-3.8-flash-tts": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_flex": 2.5e-08,
"cache_read_input_token_cost_priority": 2.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"input_cost_per_token_flex": 2.5e-07,
"input_cost_per_token_priority": 9e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 9e-06,
"output_cost_per_token": 9e-06,
"output_cost_per_token_batches": 4.5e-06,
"output_cost_per_token_flex": 4.5e-06,
"output_cost_per_token_priority": 1.62e-05,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/audio/speech"
]
},
"gemini/gemini-3.8-flash-lite-tts": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_flex": 2.5e-08,
"cache_read_input_token_cost_priority": 2.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"input_cost_per_token_flex": 2.5e-07,
"input_cost_per_token_priority": 9e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 6e-06,
"output_cost_per_token": 6e-06,
"output_cost_per_token_batches": 3e-06,
"output_cost_per_token_flex": 3e-06,
"output_cost_per_token_priority": 1.08e-05,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/audio/speech"
]
},
"gemini-2.5-flash-preview-tts": {
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,

48
model_prices_and_context_window.json
View file

@ -55199,6 +55199,54 @@
"supports_response_schema": false,
"supports_web_search": false
},
"gemini/gemini-3.8-flash-tts": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_flex": 2.5e-08,
"cache_read_input_token_cost_priority": 2.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"input_cost_per_token_flex": 2.5e-07,
"input_cost_per_token_priority": 9e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 9e-06,
"output_cost_per_token": 9e-06,
"output_cost_per_token_batches": 4.5e-06,
"output_cost_per_token_flex": 4.5e-06,
"output_cost_per_token_priority": 1.62e-05,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/audio/speech"
]
},
"gemini/gemini-3.8-flash-lite-tts": {
"cache_read_input_token_cost": 1.25e-07,
"cache_read_input_token_cost_batches": 6.25e-08,
"cache_read_input_token_cost_flex": 2.5e-08,
"cache_read_input_token_cost_priority": 2.25e-07,
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,
"input_cost_per_token_flex": 2.5e-07,
"input_cost_per_token_priority": 9e-07,
"litellm_provider": "gemini",
"max_input_tokens": 8192,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "audio_speech",
"output_cost_per_audio_token": 6e-06,
"output_cost_per_token": 6e-06,
"output_cost_per_token_batches": 3e-06,
"output_cost_per_token_flex": 3e-06,
"output_cost_per_token_priority": 1.08e-05,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/audio/speech"
]
},
"gemini-2.5-flash-preview-tts": {
"input_cost_per_token": 5e-07,
"input_cost_per_token_batches": 2.5e-07,

2
tests/test_litellm/test_utils.py
View file

@ -6142,6 +6142,8 @@ def test_get_model_info_gemini(monkeypatch):
and "veo" not in model
and "lyria" not in model
and "robotics" not in model
and "3.8-flash-tts" not in model
and "3.8-flash-lite-tts" not in model
):
assert info.get("tpm") is not None, f"{model} does not have tpm"
assert info.get("rpm") is not None, f"{model} does not have rpm"