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
Released21 Sep 202620 May 202631 Mar 2026
Status
Current
Current
Current
Open weightsNoNoNo
Hosts
APIs you can call it on
824
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atxAIxAIxAI
Input$2.00$1.00$1.25
Output$6.00$2.00$2.50
Cached input$0.50$0.20$0.20
Batch
input / output
$1.60 / $4.80-$1.00 / $2.00
Long prompts
input / output
$4.00 / $12.00
above 200K
$2.00 / $4.00
above 200K
$2.50 / $5.00
above 200K
Cheapest anywhere
input / output
$2.00 / $6.00
xAI
$1.00 / $2.00
xAI
$1.25 / $2.50
xAI
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
$915$378$468
RAG over documents
2,000 a day, 8K in, 600 out
$816$360$438
Coding agent
1,000 a day, 40K in, 2K out
$1,500$648$768
Overnight batch
20,000 a day, 4K in, 400 out
$4,992$2,880$2,880
Limits
Context window500K tokens256K tokens1M tokens
Max output500K tokens256K tokens1M tokens
Capabilities
Takes inText, ImagesText, ImagesText, Images
ProducesTextTextText
Effort settings
as listed by the source
---
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Batch API
Built-in web search