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
Released29 Feb 202417 Nov 2026
Status
Older
Current
in 90 days Leaves Azure OpenAI on 17 Feb 2027
Open weightsNoNo
Hosts
APIs you can call it on
23
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atVercel AI GatewayOpenAI
Input$15.00$8.00
Output$75.00$40.00
Cached input$1.50$0.40
Batch
input / output
-$4.00 / $20.00
Long prompts
input / output
-$16.00 / $60.00
above 272K
Cheapest anywhere
input / output
$15.00 / $75.00
Vercel AI Gateway
$8.00 / $40.00
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
$8,910$4,716
RAG over documents
2,000 a day, 8K in, 600 out
$6,660$3,456
Coding agent
1,000 a day, 40K in, 2K out
$11,160$5,616
Overnight batch
20,000 a day, 4K in, 400 out
$54,000$14,400
Limits
Context window200K tokens922K tokens
Max output4K tokens128K tokens
Capabilities
Takes inText, ImagesImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
-xhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Computer use
Parallel tool calls
Tool search