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
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
21
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNscaleMistral AI
Input$0.60$0.30
Output$0.60$0.90
Cached input-$0.03
Batch
input / output
--
Cheapest anywhere
input / output
$0.60 / $0.60
Nscale
$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
$225$133
RAG over documents
2,000 a day, 8K in, 600 out
$310$112
Coding agent
1,000 a day, 40K in, 2K out
$756$187
Overnight batch
20,000 a day, 4K in, 400 out
$1,584$936
Limits
Context window66K tokens128K tokens
Max output66K tokens128K tokens
Capabilities
Takes inTextText
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Tool calling
Assistant prefill