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
Released30 Jun 202626 Oct 2026
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
125
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAnthropicOpenAI
Input$2.00$1.00
Output$10.00$5.00
Cached input$0.20$0.05
Batch
input / output
$1.00 / $5.00$0.50 / $2.50
Long prompts
input / output
-$2.00 / $7.50
above 272K
Cheapest anywhere
input / output
$2.00 / $10.00
Databricks
$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
$1,188$590
RAG over documents
2,000 a day, 8K in, 600 out
$888$432
Coding agent
1,000 a day, 40K in, 2K out
$1,488$702
Overnight batch
20,000 a day, 4K in, 400 out
$3,600$1,800
Limits
Context window1M tokens922K tokens
Max output128K tokens128K tokens
Capabilities
Takes inText, Images, PDFsImages, Text, PDFs
ProducesTextText
Effort settings
as listed by the source
xhigh, maxnone, xhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Adaptive thinking
Built-in web search
Computer use
Native structured output
Parallel tool calls
Tool search