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
Released17 Dec 2024-
Status
Preview
Current
Open weightsNoNo
Hosts
APIs you can call it on
11
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAzure OpenAIGoogle AI Studio
Input$5.00$0.75
Output$20.00$4.50
Cached input$2.50-
Batch
input / output
--
Cheapest anywhere
input / output
$5.00 / $20.00
Azure OpenAI
$0.75 / $4.50
Google AI Studio
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
$2,775$563
RAG over documents
2,000 a day, 8K in, 600 out
$2,520$522
Coding agent
1,000 a day, 40K in, 2K out
$5,100$1,170
Overnight batch
20,000 a day, 4K in, 400 out
$16,800$2,880
Limits
Context window16K tokens131K tokens
Max output4K tokens66K tokens
Capabilities
Takes inAudio, TextAudio, Images, Text, Video
ProducesAudio, TextAudio, Text
Effort settings
as listed by the source
--
Function calling
Reasoning
Tool calling
Built-in web search
Parallel tool calls