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
Released30 Apr 202626 Feb 2024
Status
Current
Open weightsYes, otherNo
Hosts
APIs you can call it on
28
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atMistral AIMistral AI
Input$1.50$0.70
Output$7.50$2.10
Cached input$0.15$0.07
Batch
input / output
--
Cheapest anywhere
input / output
$1.50 / $7.50
Mistral AI
$0.70 / $2.10
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
$891$311
RAG over documents
2,000 a day, 8K in, 600 out
$666$260
Coding agent
1,000 a day, 40K in, 2K out
$1,116$437
Overnight batch
20,000 a day, 4K in, 400 out
$5,400$2,184
Limits
Context window262K tokens1M tokens
Max output262K tokens1M tokens
Capabilities
Takes inText, ImagesText, Images
ProducesTextText
Effort settings
as listed by the source
none, highlow, medium, high
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Assistant prefill