mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-08 22:21:35 +00:00
feat(vertex): add gemini-3.1-flash-image-preview model DB support
- add gemini-3.1-flash-image-preview + vertex_ai alias entries\n- set pricing to Gemini 3.1 Flash Image Preview rates\n- mirror updates in packaged backup model map\n- update llm cost calc regression test to cover new model
This commit is contained in:
Emerson Gomes
Sameer Kankute
parent
b1ade5fbd7
commit
5eece691db
3 changed files with 106 additions and 11 deletions
|
|
@ -14194,6 +14194,38 @@
|
|||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"gemini-3.1-flash-image-preview": {
|
||||
"input_cost_per_image": 0.00056,
|
||||
"input_cost_per_token": 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": 0.0672,
|
||||
"output_cost_per_image_token": 6e-05,
|
||||
"output_cost_per_token": 3e-06,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
|
||||
"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
|
||||
},
|
||||
"deep-research-pro-preview-12-2025": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
"input_cost_per_token": 2e-06,
|
||||
|
|
@ -31545,6 +31577,19 @@
|
|||
"output_cost_per_token_batches": 6e-06,
|
||||
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
|
||||
},
|
||||
"vertex_ai/gemini-3.1-flash-image-preview": {
|
||||
"input_cost_per_image": 0.00056,
|
||||
"input_cost_per_token": 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": 0.0672,
|
||||
"output_cost_per_image_token": 6e-05,
|
||||
"output_cost_per_token": 3e-06,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
|
||||
},
|
||||
"vertex_ai/deep-research-pro-preview-12-2025": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
"input_cost_per_token": 2e-06,
|
||||
|
|
|
|||
|
|
@ -14194,6 +14194,38 @@
|
|||
"supports_vision": true,
|
||||
"supports_web_search": true
|
||||
},
|
||||
"gemini-3.1-flash-image-preview": {
|
||||
"input_cost_per_image": 0.00056,
|
||||
"input_cost_per_token": 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": 0.0672,
|
||||
"output_cost_per_image_token": 6e-05,
|
||||
"output_cost_per_token": 3e-06,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
|
||||
"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
|
||||
},
|
||||
"deep-research-pro-preview-12-2025": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
"input_cost_per_token": 2e-06,
|
||||
|
|
@ -31545,6 +31577,19 @@
|
|||
"output_cost_per_token_batches": 6e-06,
|
||||
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
|
||||
},
|
||||
"vertex_ai/gemini-3.1-flash-image-preview": {
|
||||
"input_cost_per_image": 0.00056,
|
||||
"input_cost_per_token": 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": 0.0672,
|
||||
"output_cost_per_image_token": 6e-05,
|
||||
"output_cost_per_token": 3e-06,
|
||||
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
|
||||
},
|
||||
"vertex_ai/deep-research-pro-preview-12-2025": {
|
||||
"input_cost_per_image": 0.0011,
|
||||
"input_cost_per_token": 2e-06,
|
||||
|
|
|
|||
|
|
@ -766,7 +766,14 @@ def test_service_tier_fallback_pricing():
|
|||
assert abs(std_cost[1] - expected_standard_completion) < 1e-10, f"Standard completion cost mismatch: {std_cost[1]} vs {expected_standard_completion}"
|
||||
|
||||
|
||||
def test_gemini_image_generation_cost_with_zero_text_tokens():
|
||||
@pytest.mark.parametrize(
|
||||
"model",
|
||||
[
|
||||
"gemini-3-pro-image-preview",
|
||||
"gemini-3.1-flash-image-preview",
|
||||
],
|
||||
)
|
||||
def test_gemini_image_generation_cost_with_zero_text_tokens(model: str):
|
||||
"""
|
||||
Test that image_tokens are correctly costed when text_tokens=0.
|
||||
|
||||
|
|
@ -779,7 +786,6 @@ def test_gemini_image_generation_cost_with_zero_text_tokens():
|
|||
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
|
||||
litellm.model_cost = litellm.get_model_cost_map(url="")
|
||||
|
||||
model = "gemini-3-pro-image-preview"
|
||||
custom_llm_provider = "vertex_ai"
|
||||
|
||||
# Usage from the issue: text_tokens=0, image_tokens=1120, reasoning_tokens=225
|
||||
|
|
@ -809,9 +815,9 @@ def test_gemini_image_generation_cost_with_zero_text_tokens():
|
|||
|
||||
# Expected costs:
|
||||
# - text_tokens: 0 * output_cost_per_token = 0
|
||||
# - image_tokens: 1120 * output_cost_per_image_token = 1120 * 1.2e-04 = 0.1344
|
||||
# - reasoning_tokens: 225 * output_cost_per_token = 225 * 1.2e-05 = 0.0027
|
||||
# Total completion: ~0.1371
|
||||
# - image_tokens: 1120 * output_cost_per_image_token
|
||||
# - reasoning_tokens: 225 * output_cost_per_token
|
||||
# Total completion should include both image + reasoning costs.
|
||||
|
||||
output_cost_per_image_token = model_cost_map.get("output_cost_per_image_token", 0)
|
||||
output_cost_per_token = model_cost_map.get("output_cost_per_token", 0)
|
||||
|
|
@ -820,12 +826,11 @@ def test_gemini_image_generation_cost_with_zero_text_tokens():
|
|||
expected_reasoning_cost = 225 * output_cost_per_token # reasoning uses base token cost
|
||||
expected_completion_cost = expected_image_cost + expected_reasoning_cost
|
||||
|
||||
# The bug was: all 1345 tokens were treated as text = 1345 * 1.2e-05 = 0.01614
|
||||
# Fixed: image_tokens use image pricing = ~0.137
|
||||
|
||||
assert completion_cost > 0.10, (
|
||||
f"Completion cost should be > $0.10 (image tokens are expensive), got ${completion_cost:.6f}. "
|
||||
f"Bug: tokens may be incorrectly treated as text tokens."
|
||||
# The bug was: all completion tokens were treated as text tokens only.
|
||||
bugged_text_only_cost = 1345 * output_cost_per_token
|
||||
assert completion_cost > bugged_text_only_cost * 2, (
|
||||
f"Completion cost should be significantly larger than text-only bugged path. "
|
||||
f"Expected > {bugged_text_only_cost * 2:.6f}, got {completion_cost:.6f}"
|
||||
)
|
||||
assert round(completion_cost, 4) == round(expected_completion_cost, 4), (
|
||||
f"Expected completion cost ${expected_completion_cost:.6f}, got ${completion_cost:.6f}"
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue