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
Released9 Aug 20262 Sep 2026
Status
Current
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
62
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atDeepInfraMeta Model API
Input$0.30$0.10
Output$1.20$0.20
Cached input$0.04$0.002
Batch
input / output
--
Cheapest anywhere
input / output
$0.20 / $0.80
EmpirioLabs AI
$0.10 / $0.20
Meta Model API
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
$157$36.18
RAG over documents
2,000 a day, 8K in, 600 out
$125$31.68
Coding agent
1,000 a day, 40K in, 2K out
$214$49.68
Overnight batch
20,000 a day, 4K in, 400 out
$1,008$288
Limits
Context window131K tokens1M tokens
Max output131K tokens131K tokens
Capabilities
Takes inText, ImagesImages, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
-minimal, xhigh
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Built-in web search
Parallel tool calls