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-24 Feb 2026
Status
Current
Current
in 133 days Leaves OpenAI on 1 Apr 2027
Open weightsYes, Modified MIT LicenseNo
Hosts
APIs you can call it on
15
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAzure AI FoundryOpenAI
Input$3.00$1.75
Output$15.00$14.00
Cached input$0.30$0.175
Batch
input / output
--
Cheapest anywhere
input / output
$3.00 / $15.00
Azure AI Foundry
$1.75 / $14.00
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
$1,782$1,433
RAG over documents
2,000 a day, 8K in, 600 out
$1,332$966
Coding agent
1,000 a day, 40K in, 2K out
$2,232$1,617
Overnight batch
20,000 a day, 4K in, 400 out
$10,800$7,560
Limits
Context window1M tokens272K tokens
Max output131K tokens128K tokens
Capabilities
Takes inImages, TextImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
none, minimal, low, medium, high, xhigh, maxnone, xhigh
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Built-in web search
Parallel tool calls
Tool search