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
Released3 Jun 202617 Mar 2026
Status
Older
Current
in 133 days Leaves OpenAI on 1 Apr 2027
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
18
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atKyma APIOpenAI
Input$0.432$0.20
Output$1.73$1.25
Cached input$0.0864$0.02
Batch
input / output
-$0.10 / $0.625
Long prompts
input / output
$1.30 / $5.18
above 256K
-
Cheapest anywhere
input / output
$0.432 / $1.73
Kyma API
$0.20 / $1.25
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
$228$138
RAG over documents
2,000 a day, 8K in, 600 out
$187$97.80
Coding agent
1,000 a day, 40K in, 2K out
$332$164
Overnight batch
20,000 a day, 4K in, 400 out
$1,453$390
Limits
Context window1M tokens272K tokens
Max output33K tokens128K tokens
Capabilities
Takes inText, ImagesImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
-none, xhigh
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Parallel tool calls