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
Released16 Jul 202617 Mar 2026
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
37
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atMeta Model APIOpenAI
Input$1.25$0.75
Output$4.25$4.50
Cached input$0.15$0.075
Batch
input / output
-$0.375 / $2.25
Cheapest anywhere
input / output
$1.25 / $4.25
Meta Model API
$0.75 / $4.50
Databricks
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
$595$502
RAG over documents
2,000 a day, 8K in, 600 out
$489$360
Coding agent
1,000 a day, 40K in, 2K out
$831$603
Overnight batch
20,000 a day, 4K in, 400 out
$4,020$1,440
Limits
Context window1M tokens272K tokens
Max output131K tokens128K tokens
Capabilities
Takes inImages, Text, Video, PDFsImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
minimal, xhighnone, xhigh
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Parallel tool calls
Tool search