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
Released-2 Sep 2026
Status
Preview
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
16
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAIHubMixGoogle AI Studio
Input$1.27$0.75
Output$7.61$3.75
Cached input$0.127$0.075
Batch
input / output
-$0.375 / $1.88
Cheapest anywhere
input / output
$1.27 / $7.61
AIHubMix
$0.75 / $3.75
Databricks
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
$848$446
RAG over documents
2,000 a day, 8K in, 600 out
$609$333
Coding agent
1,000 a day, 40K in, 2K out
$1,019$558
Overnight batch
20,000 a day, 4K in, 400 out
$4,869$1,350
Limits
Context window262K tokens1M tokens
Max output66K tokens66K tokens
Capabilities
Takes inTextAudio, 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