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
Released16 Mar 2026-
Status
Current
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
12
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atMistral AIMistral AI
Input$0.15$0.10
Output$0.60$0.30
Cached input$0.015$0.01
Batch
input / output
--
Cheapest anywhere
input / output
$0.15 / $0.60
Mistral AI
$0.07 / $0.28
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
$77.85$44.40
RAG over documents
2,000 a day, 8K in, 600 out
$61.20$37.20
Coding agent
1,000 a day, 40K in, 2K out
$103$62.40
Overnight batch
20,000 a day, 4K in, 400 out
$504$312
Limits
Context window262K tokens256K tokens
Max output262K tokens256K tokens
Capabilities
Takes inText, ImagesText
ProducesTextText
Effort settings
as listed by the source
none, highnone, high
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Assistant prefill