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
Released9 Nov 20265 Nov 20264 Nov 2026
Status
Current
Current
Preview
Open weightsYes, Apache-2.0NoYes, Apache-2.0
Hosts
APIs you can call it on
312
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atCloudflare Workers AINot listedGMI Cloud
Input$0.30-$0.20
Output$1.00-$0.60
Cached input$0.10-$0.05
Batch
input / output
---
Cheapest anywhere
input / output
$0.30 / $1.00
Cloudflare Workers AI
Not listed$0.20 / $0.60
GMI Cloud
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
$147-$91.50
RAG over documents
2,000 a day, 8K in, 600 out
$132-$81.60
Coding agent
1,000 a day, 40K in, 2K out
$252-$150
Overnight batch
20,000 a day, 4K in, 400 out
$960-$624
Limits
Context window1M tokens-1M tokens
Max output1M tokens-131K tokens
Capabilities
Takes inText, ImagesTextText
ProducesTextTextText
Effort settings
as listed by the source
---
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling