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
Released14 May 202518 Nov 2026
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
62
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atSnowflakeGoogle AI Studio
Input$5.00$3.00
Output$25.00$15.00
Cached input$0.50$0.15
Batch
input / output
-$1.50 / $7.50
Cheapest anywhere
input / output
$5.00 / $25.00
Snowflake
$3.00 / $15.00
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
$2,970$1,769
RAG over documents
2,000 a day, 8K in, 600 out
$2,220$1,296
Coding agent
1,000 a day, 40K in, 2K out
$3,720$2,106
Overnight batch
20,000 a day, 4K in, 400 out
$18,000$5,400
Limits
Context window200K tokens1M tokens
Max output16K tokens1M tokens
Capabilities
Takes inText, ImagesAudio, Images, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
-xhigh
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