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
Released31 Oct 20255 Dec 2024
Status
Current
Current
Open weightsNoNo
Hosts
APIs you can call it on
23
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon NovaAmazon Nova
Input$2.50$0.80
Output$12.50$3.20
Cached input--
Batch
input / output
--
Cheapest anywhere
input / output
$2.50 / $12.50
Amazon Nova
$0.80 / $3.20
Amazon Nova
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
$1,688$480
RAG over documents
2,000 a day, 8K in, 600 out
$1,650$499
Coding agent
1,000 a day, 40K in, 2K out
$3,750$1,152
Overnight batch
20,000 a day, 4K in, 400 out
$9,000$2,688
Limits
Context window1M tokens300K tokens
Max output10K tokens10K tokens
Capabilities
Takes inText, Images, PDFsText, Images, PDFs
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Tool calling
Prompt caching