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
Released21 May 202626 Oct 2026
Status
Older
Newer: Qwen4 Max
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
15
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atKyma APIOpenAI
Input$2.07$1.00
Output$6.21$5.00
Cached input$0.169$0.05
Batch
input / output
-$0.50 / $2.50
Long prompts
input / output
-$2.00 / $7.50
above 272K
Cheapest anywhere
input / output
$2.07 / $6.21
Kyma API
$1.00 / $5.00
OpenAI
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
$916$590
RAG over documents
2,000 a day, 8K in, 600 out
$761$432
Coding agent
1,000 a day, 40K in, 2K out
$1,260$702
Overnight batch
20,000 a day, 4K in, 400 out
$6,460$1,800
Limits
Context window1M tokens922K tokens
Max output33K tokens128K tokens
Capabilities
Takes inTextImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
-none, xhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search
Computer use
Parallel tool calls
Tool search