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
Released31 Mar 202620 May 2026
Status
Older
Newer: Grok 4.7
Current
Open weightsNoNo
Hosts
APIs you can call it on
32
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atxAIxAI
Input$1.25$1.00
Output$2.50$2.00
Cached input$0.20$0.20
Batch
input / output
$1.00 / $2.00-
Long prompts
input / output
$2.50 / $5.00
above 200K
$2.00 / $4.00
above 200K
Cheapest anywhere
input / output
$1.25 / $2.50
xAI
$1.00 / $2.00
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
$468$378
RAG over documents
2,000 a day, 8K in, 600 out
$438$360
Coding agent
1,000 a day, 40K in, 2K out
$768$648
Overnight batch
20,000 a day, 4K in, 400 out
$2,880$2,880
Limits
Context window1M tokens256K tokens
Max output1M tokens256K tokens
Capabilities
Takes inText, ImagesText, Images
ProducesTextText
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