impulse

Compare models

Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.

Clear
Model
Overview
Released13 Aug 202621 Jul 2026
Status
Older
in 70 days Leaves Vertex AI on 28 Jan 2027
Current
Open weightsNoNo
Hosts
APIs you can call it on
87
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atGoogle AI StudioGoogle AI Studio
Input$0.75$0.30
Output$3.75$2.50
Cached input$0.075$0.03
Batch
input / output
$0.375 / $1.88$0.15 / $1.25
Cheapest anywhere
input / output
$0.75 / $3.75
Databricks
$0.30 / $2.50
AIHubMix
Monthly bill · at the price above, 30 days, with each workload's cache and batch use
Chat assistant
5,000 a day, 2K in, 500 out
$446$253
RAG over documents
2,000 a day, 8K in, 600 out
$333$169
Coding agent
1,000 a day, 40K in, 2K out
$558$283
Overnight batch
20,000 a day, 4K in, 400 out
$1,350$660
Limits
Context window1M tokens1M tokens
Max output66K tokens66K tokens
Capabilities
Takes inAudio, Images, Text, Video, PDFsAudio, Images, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Computer use
Parallel tool calls
URL context