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
Released9 Jul 202628 Sep 2026
Status
Older
Current
Open weightsNoNo
Hosts
APIs you can call it on
88
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atOpenAIAnthropic
Input$4.00$2.00
Output$20.00$10.00
Cached input$0.40$0.10
Batch
input / output
$2.00 / $10.00$1.00 / $5.00
Long prompts
input / output
$8.00 / $30.00
above 272K
-
Cheapest anywhere
input / output
$2.00 / $10.00
Replicate
$2.00 / $10.00
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
$2,376$1,179
RAG over documents
2,000 a day, 8K in, 600 out
$1,776$864
Coding agent
1,000 a day, 40K in, 2K out
$2,976$1,404
Overnight batch
20,000 a day, 4K in, 400 out
$7,200$3,600
Limits
Context window922K tokens1M tokens
Max output128K tokens128K tokens
Capabilities
Takes inImages, Text, PDFsText, Images, PDFs
ProducesTextText
Effort settings
as listed by the source
none, xhighxhigh, 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
Native structured output
Parallel tool calls
Tool search