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
Released17 Feb 202621 Sep 2026
Status
Older
in 83 days Leaves Azure AI Foundry on 10 Feb 2027
Current
Open weightsNoNo
Hosts
APIs you can call it on
108
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAnthropicxAI
Input$3.00$2.00
Output$15.00$6.00
Cached input$0.30$0.50
Batch
input / output
$1.50 / $7.50$1.60 / $4.80
Long prompts
input / output
-$4.00 / $12.00
above 200K
Cheapest anywhere
input / output
$3.00 / $15.00
Databricks
$2.00 / $6.00
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
$1,782$915
RAG over documents
2,000 a day, 8K in, 600 out
$1,332$816
Coding agent
1,000 a day, 40K in, 2K out
$2,232$1,500
Overnight batch
20,000 a day, 4K in, 400 out
$5,400$4,992
Limits
Context window1M tokens500K tokens
Max output128K tokens500K tokens
Capabilities
Takes inText, Images, PDFsText, Images
ProducesTextText
Effort settings
as listed by the source
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