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
Released-
Status
Current
Open weightsNo
Hosts
APIs you can call it on
1
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atOpenAI
Input$20.00
Output$100.00
Cached input$2.00
Batch
input / output
-
Long prompts
input / output
$40.00 / $150.00
above 272K
Cheapest anywhere
input / output
$20.00 / $100.00
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
$11,880
RAG over documents
2,000 a day, 8K in, 600 out
$8,880
Coding agent
1,000 a day, 40K in, 2K out
$14,880
Overnight batch
20,000 a day, 4K in, 400 out
$72,000
Limits
Context window922K tokens
Max output128K tokens
Capabilities
Takes inImages, Text, PDFs
ProducesText
Effort settings
as listed by the source
-
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Built-in web search
Computer use
Tool search