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
Released7 May 202526 Oct 2026
Status
Current
Open weightsNoNo
Hosts
APIs you can call it on
25
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atMistral AIOpenAI
Input$1.50$1.00
Output$7.50$5.00
Cached input$0.15$0.05
Batch
input / output
-$0.50 / $2.50
Long prompts
input / output
-$2.00 / $7.50
above 272K
Cheapest anywhere
input / output
$0.40 / $2.00
Vertex AI
$1.00 / $5.00
OpenAI
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$590
RAG over documents
2,000 a day, 8K in, 600 out
$666$432
Coding agent
1,000 a day, 40K in, 2K out
$1,116$702
Overnight batch
20,000 a day, 4K in, 400 out
$5,400$1,800
Limits
Context window262K tokens922K tokens
Max output262K tokens128K tokens
Capabilities
Takes inText, ImagesImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
none, highnone, xhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Assistant prefill
Built-in web search
Computer use
Parallel tool calls
Tool search