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-12 Nov 2026
Status
Current
Current
Open weightsNoNo
Hosts
APIs you can call it on
13
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAzure AI FoundryGoogle AI Studio
Input$2.31$1.50
Output$7.26$7.50
Cached input$0.231$0.075
Batch
input / output
-$0.75 / $3.75
Cheapest anywhere
input / output
$2.31 / $7.26
Azure AI Foundry
$1.50 / $7.50
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
$1,050$884
RAG over documents
2,000 a day, 8K in, 600 out
$871$648
Coding agent
1,000 a day, 40K in, 2K out
$1,461$1,053
Overnight batch
20,000 a day, 4K in, 400 out
$7,286$2,700
Limits
Context window1M tokens1M tokens
Max output131K tokens1M tokens
Capabilities
Takes inTextAudio, Images, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
-xhigh
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Computer use
Parallel tool calls
URL context