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
Released19 Feb 2026
Status
Preview
Open weightsNo
Hosts
APIs you can call it on
5
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atGoogle AI Studio
Input$2.00
Output$12.00
Cached input$0.20
Batch
input / output
$1.00 / $6.00
Long prompts
input / output
$4.00 / $18.00
above 200K
Cheapest anywhere
input / output
$2.00 / $12.00
Google AI Studio
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
$1,338
RAG over documents
2,000 a day, 8K in, 600 out
$960
Coding agent
1,000 a day, 40K in, 2K out
$1,608
Overnight batch
20,000 a day, 4K in, 400 out
$3,840
Limits
Context window1M tokens
Max output66K tokens
Capabilities
Takes inAudio, Images, Text, Video, PDFs
ProducesText
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
URL context