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
Released5 Apr 20252 Sep 2026
Status
Current
today Leaves Azure AI Foundry on 19 Nov 2026
Current
Open weightsYes, Llama Community LicenseNo
Hosts
APIs you can call it on
103
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNot listedMeta Model API
Input-$1.25
Output-$4.25
Cached input-$0.15
Batch
input / output
--
Cheapest anywhere
input / output
$0.05 / $0.10
Lambda AI
$1.25 / $4.25
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
-$595
RAG over documents
2,000 a day, 8K in, 600 out
-$489
Coding agent
1,000 a day, 40K in, 2K out
-$831
Overnight batch
20,000 a day, 4K in, 400 out
-$4,020
Limits
Context window1M tokens1M tokens
Max output4K tokens131K tokens
Capabilities
Takes inImages, TextImages, 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