feat(vertex_ai): add gemini-3.8-flash-cyber pricing (#42879)
Some checks failed
LiteLLM Rust / rust-lint (push) Waiting to run
LiteLLM Rust / rust-test (push) Waiting to run
LiteLLM Rust / rust-wheel (push) Waiting to run
Terraform Provider / gofmt, vet, build, test (push) Waiting to run
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Waiting to run
Terraform Modules / fmt, validate, test (aws) (push) Has been cancelled
Terraform Modules / fmt, validate, test (gcp) (push) Has been cancelled

* feat(vertex_ai): add gemini-3.8-flash-cyber pricing

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

* fix(vertex_ai): mark gemini-3.8-flash-cyber minimal reasoning unsupported

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 21:55:55 -07:00 • committed by GitHub
parent 9d12c217af
commit b21b20ed13
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 184 additions and 0 deletions

View file

@ -27336,6 +27336,52 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"vertex_ai/gemini-3.8-flash-cyber": {
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_flex": 7.5e-08,
"cache_read_input_token_cost_priority": 2.7e-07,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_flex": 7.5e-07,
"input_cost_per_token_priority": 2.7e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 7.5e-06,
"output_cost_per_token": 7.5e-06,
"output_cost_per_token_flex": 3.75e-06,
"output_cost_per_token_priority": 1.35e-05,
"regional_endpoint_uplift_multiplier": 1.1,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_function_calling": false,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_minimal_reasoning_effort": false,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": false,
"supports_url_context": false,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": false,
"supports_native_streaming": true
},
"vertex_ai/gemini-3.1-pro-preview": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 2e-07,
@ -29508,6 +29554,52 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-3.8-flash-cyber": {
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_flex": 7.5e-08,
"cache_read_input_token_cost_priority": 2.7e-07,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_flex": 7.5e-07,
"input_cost_per_token_priority": 2.7e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 7.5e-06,
"output_cost_per_token": 7.5e-06,
"output_cost_per_token_flex": 3.75e-06,
"output_cost_per_token_priority": 1.35e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": false,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_minimal_reasoning_effort": false,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": false,
"supports_url_context": false,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": false,
"supports_native_streaming": true
},
"gemini/gemini-2.5-pro-preview-tts": {
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_audio_token": 7e-07,

View file

@ -27336,6 +27336,52 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"vertex_ai/gemini-3.8-flash-cyber": {
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_flex": 7.5e-08,
"cache_read_input_token_cost_priority": 2.7e-07,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_flex": 7.5e-07,
"input_cost_per_token_priority": 2.7e-06,
"litellm_provider": "vertex_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 7.5e-06,
"output_cost_per_token": 7.5e-06,
"output_cost_per_token_flex": 3.75e-06,
"output_cost_per_token_priority": 1.35e-05,
"regional_endpoint_uplift_multiplier": 1.1,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_function_calling": false,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_minimal_reasoning_effort": false,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": false,
"supports_url_context": false,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": false,
"supports_native_streaming": true
},
"vertex_ai/gemini-3.1-pro-preview": {
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 2e-07,
@ -29508,6 +29554,52 @@
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-3.8-flash-cyber": {
"cache_read_input_token_cost": 1.5e-07,
"cache_read_input_token_cost_flex": 7.5e-08,
"cache_read_input_token_cost_priority": 2.7e-07,
"input_cost_per_token": 1.5e-06,
"input_cost_per_token_flex": 7.5e-07,
"input_cost_per_token_priority": 2.7e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 7.5e-06,
"output_cost_per_token": 7.5e-06,
"output_cost_per_token_flex": 3.75e-06,
"output_cost_per_token_priority": 1.35e-05,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": false,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_minimal_reasoning_effort": false,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": false,
"supports_url_context": false,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": false,
"supports_native_streaming": true
},
"gemini/gemini-2.5-pro-preview-tts": {
"cache_read_input_token_cost": 1.25e-07,
"input_cost_per_audio_token": 7e-07,