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 Oct 20252 Sep 2026
Status
Older
in 95 days Leaves Azure AI Foundry on 22 Feb 2027
Current
Open weightsNoNo
Hosts
APIs you can call it on
126
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAnthropicGoogle AI Studio
Input$1.00$0.75
Output$5.00$3.75
Cached input$0.10$0.075
Batch
input / output
$0.50 / $2.50$0.375 / $1.88
Cheapest anywhere
input / output
$1.00 / $5.00
Anthropic
$0.75 / $3.75
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
$594$446
RAG over documents
2,000 a day, 8K in, 600 out
$444$333
Coding agent
1,000 a day, 40K in, 2K out
$744$558
Overnight batch
20,000 a day, 4K in, 400 out
$1,800$1,350
Limits
Context window200K tokens1M tokens
Max output64K tokens66K tokens
Capabilities
Takes inText, Images, PDFsAudio, Images, Text, Video, PDFs
ProducesTextText
Effort settings
as listed by the source
--
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Assistant prefill
Built-in web search
Computer use
Native structured output
Parallel tool calls
URL context