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-21 Jul 2026
Status
Current
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
27
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNovita AIGoogle AI Studio
Input$0.60$0.30
Output$2.40$2.50
Cached input$0.06$0.03
Batch
input / output
-$0.15 / $1.25
Cheapest anywhere
input / output
$0.30 / $1.20
EmpirioLabs AI
$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
$311$253
RAG over documents
2,000 a day, 8K in, 600 out
$245$169
Coding agent
1,000 a day, 40K in, 2K out
$410$283
Overnight batch
20,000 a day, 4K in, 400 out
$2,016$660
Limits
Context window205K tokens1M tokens
Max output131K 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