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
Released1 Sep 20269 Nov 2026
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
77
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAnthropicAnthropic
Input$10.00$8.00
Output$50.00$40.00
Cached input$0.25$0.20
Batch
input / output
$5.00 / $25.00$4.00 / $20.00
Cheapest anywhere
input / output
$10.00 / $50.00
Databricks
$8.00 / $40.00
Anthropic
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
$5,873$4,698
RAG over documents
2,000 a day, 8K in, 600 out
$4,260$3,408
Coding agent
1,000 a day, 40K in, 2K out
$6,810$5,448
Overnight batch
20,000 a day, 4K in, 400 out
$18,000$14,400
Limits
Context window1M tokens1M tokens
Max output128K tokens128K tokens
Capabilities
Takes inText, Images, PDFsText, Images, PDFs
ProducesTextText
Effort settings
as listed by the source
xhigh, maxxhigh, max
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Adaptive thinking
Always reasons
Built-in web search
Computer use
Fast mode
Native structured output