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
Released12 Feb 2026
Status
Older
Newer: MiniMax M3
Open weightsYes, Apache-2.0
Hosts
APIs you can call it on
9
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atMiniMax
Input$0.30
Output$1.20
Cached input$0.03
Batch
input / output
-
Cheapest anywhere
input / output
$0.30 / $1.20
MiniMax
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
$156
RAG over documents
2,000 a day, 8K in, 600 out
$122
Coding agent
1,000 a day, 40K in, 2K out
$205
Overnight batch
20,000 a day, 4K in, 400 out
$1,008
Limits
Context window1M tokens
Max output8K tokens
Capabilities
Takes inText
ProducesText
Effort settings
as listed by the source
-
Streaming
Function calling
Reasoning
Tool calling
Prompt caching