mirror of
https://github.com/CherryHQ/cherry-studio.git
synced 2026-01-05 04:19:02 +08:00
40 lines
1.8 KiB
YAML
40 lines
1.8 KiB
YAML
id: google/gemini-2.5-flash-preview:thinking
|
|
canonical_slug: google/gemini-2.5-flash-preview-04-17
|
|
hugging_face_id: ''
|
|
name: 'Google: Gemini 2.5 Flash Preview 04-17 (thinking)'
|
|
type: chat
|
|
created: 1744914667
|
|
description: "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nNote: This model is available in two variants: thinking and non-thinking. The output pricing varies significantly depending on whether the thinking capability is active. If you select the standard variant (without the \":thinking\" suffix), the model will explicitly avoid generating thinking tokens. \n\nTo utilize the thinking capability and receive thinking tokens, you must choose the \":thinking\" variant, which will then incur the higher thinking-output pricing. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning)."
|
|
context_length: 1048576
|
|
architecture:
|
|
modality: text+image->text
|
|
input_modalities:
|
|
- image
|
|
- text
|
|
- file
|
|
output_modalities:
|
|
- text
|
|
tokenizer: Gemini
|
|
instruct_type: null
|
|
pricing:
|
|
prompt: '0.00000015'
|
|
completion: '0.0000035'
|
|
input_cache_read: '0.0000000375'
|
|
input_cache_write: '0.0000002333'
|
|
request: '0'
|
|
image: '0.0006192'
|
|
web_search: '0'
|
|
internal_reasoning: '0'
|
|
unit: 1
|
|
currency: USD
|
|
supported_parameters:
|
|
- max_tokens
|
|
- temperature
|
|
- top_p
|
|
- tools
|
|
- tool_choice
|
|
- stop
|
|
- response_format
|
|
- structured_outputs
|
|
model_provider: google
|