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
Released11 Mar 2025
Status
Preview
Open weightsNo
Hosts
APIs you can call it on
2
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atOpenAI
Input$3.00
Output$12.00
Cached input-
Batch
input / output
-
Cheapest anywhere
input / output
$3.00 / $12.00
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
$1,800
RAG over documents
2,000 a day, 8K in, 600 out
$1,872
Coding agent
1,000 a day, 40K in, 2K out
$4,320
Overnight batch
20,000 a day, 4K in, 400 out
$10,080
Limits
Context window8K tokens
Max output1K tokens
Capabilities
Takes inImages, Text, PDFs
ProducesText
Effort settings
as listed by the source
-
Streaming
Function calling
Reasoning
Tool calling
Parallel tool calls