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
Released6 Dec 2024
Status
Current
in 73 days Leaves Azure AI Foundry on 31 Jan 2027
Open weightsYes, Llama Community License
Hosts
APIs you can call it on
16
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atNot listed
Input-
Output-
Cached input-
Batch
input / output
-
Cheapest anywhere
input / output
$0.12 / $0.30
Hyperbolic
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
-
RAG over documents
2,000 a day, 8K in, 600 out
-
Coding agent
1,000 a day, 40K in, 2K out
-
Overnight batch
20,000 a day, 4K in, 400 out
-
Limits
Context window128K tokens
Max output4K tokens
Capabilities
Takes inText
ProducesText
Effort settings
as listed by the source
-
Streaming
Function calling
Tool calling