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
Released27 Jan 2026
Status
Older
in 68 days Leaves Azure AI Foundry on 26 Jan 2027
Newer: Kimi K3.1
Open weightsYes, Modified MIT License
Hosts
APIs you can call it on
10
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atMoonshot AI
Input$0.60
Output$3.00
Cached input$0.10
Batch
input / output
-
Cheapest anywhere
input / output
$0.45 / $2.25
DeepInfra
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
$360
RAG over documents
2,000 a day, 8K in, 600 out
$276
Coding agent
1,000 a day, 40K in, 2K out
$480
Overnight batch
20,000 a day, 4K in, 400 out
$2,160
Limits
Context window262K tokens
Max output262K tokens
Capabilities
Takes inText, Images, Video
ProducesText
Effort settings
as listed by the source
-
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling