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-1 Aug 2025
Status
Current
in 131 days Leaves Amazon Bedrock on 30 Mar 2027
Current
Open weightsNoNo
Hosts
APIs you can call it on
11
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAmazon BedrockMistral AI
Input$0.40$0.30
Output$2.00$0.90
Cached input-$0.03
Batch
input / output
$0.20 / $1.00-
Cheapest anywhere
input / output
$0.40 / $2.00
Amazon Bedrock
$0.30 / $0.90
Mistral AI
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
$270$133
RAG over documents
2,000 a day, 8K in, 600 out
$264$112
Coding agent
1,000 a day, 40K in, 2K out
$600$187
Overnight batch
20,000 a day, 4K in, 400 out
$720$936
Limits
Context window256K tokens128K tokens
Max output32K tokens128K tokens
Capabilities
Takes inTextText
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Tool calling
Batch API
Assistant prefill