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
Released26 Oct 20267 Oct 2026
Status
Current
Current
Open weightsNoNo
Hosts
APIs you can call it on
59
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atOpenAIAnthropic
Input$1.00$0.10
Output$5.00$0.50
Cached input$0.05$0.01
Batch
input / output
$0.50 / $2.50$0.05 / $0.25
Long prompts
input / output
$2.00 / $7.50
above 272K
$0.50 / $2.50
above 100K
Cheapest anywhere
input / output
$1.00 / $5.00
OpenAI
$0.10 / $0.50
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
$590$59.40
RAG over documents
2,000 a day, 8K in, 600 out
$432$44.40
Coding agent
1,000 a day, 40K in, 2K out
$702$74.40
Overnight batch
20,000 a day, 4K in, 400 out
$1,800$180
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, xhigh, maxxhigh, 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