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-
Status
Open weightsYes, Apache-2.0
Hosts
APIs you can call it on
1
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atEmpirioLabs AI
Input$0.029
Output$0.287
Cached input-
Batch
input / output
-
Long prompts
input / output
$0.115 / $1.15
above 128K
Cheapest anywhere
input / output
$0.029 / $0.287
EmpirioLabs AI
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
$30.23
RAG over documents
2,000 a day, 8K in, 600 out
$24.25
Coding agent
1,000 a day, 40K in, 2K out
$52.02
Overnight batch
20,000 a day, 4K in, 400 out
$138
Limits
Context window996K tokens
Max output66K tokens
Capabilities
Takes inText, Images
ProducesText
Effort settings
as listed by the source
-
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Built-in web search