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
Released27 Apr 20267 Oct 2026
Status
Current
Current
Open weightsYes, Apache-2.0No
Hosts
APIs you can call it on
129
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atW&B InferenceAnthropic
Input$0.10$0.10
Output$0.89$0.50
Cached input$0.035$0.01
Batch
input / output
-$0.05 / $0.25
Long prompts
input / output
-$0.50 / $2.50
above 100K
Cheapest anywhere
input / output
$0.05 / $0.40
Sail
$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
$90.90$59.40
RAG over documents
2,000 a day, 8K in, 600 out
$64.44$44.40
Coding agent
1,000 a day, 40K in, 2K out
$119$74.40
Overnight batch
20,000 a day, 4K in, 400 out
$454$180
Limits
Context window262K tokens1M tokens
Max output262K tokens128K tokens
Capabilities
Takes inText, ImagesText, Images, PDFs
ProducesTextText
Effort settings
as listed by the source
-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