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--
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
22
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon BedrockMistral AI
Input$4.00$1.50
Output$12.00$7.50
Cached input-$0.15
Batch
input / output
--
Cheapest anywhere
input / output
$4.00 / $12.00
Amazon Bedrock
$2.00 / $5.00
Vercel AI Gateway
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
$2,100$891
RAG over documents
2,000 a day, 8K in, 600 out
$2,352$666
Coding agent
1,000 a day, 40K in, 2K out
$5,520$1,116
Overnight batch
20,000 a day, 4K in, 400 out
$12,480$5,400
Limits
Context window32K tokens262K tokens
Max output4K tokens262K tokens
Capabilities
Takes inTextText, Images
ProducesTextText
Effort settings
as listed by the source
-none, high
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Assistant prefill