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
Released26 Jun 202522 Sep 2026
Status
Older
today Leaves Azure OpenAI on 19 Nov 2026
Current
Open weightsNoNo
Hosts
APIs you can call it on
29
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atOpenAIAnthropic
Input$10.00$4.00
Output$40.00$20.00
Cached input$2.50$0.20
Batch
input / output
-$2.00 / $10.00
Cheapest anywhere
input / output
$10.00 / $40.00
OpenAI
$4.00 / $20.00
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
$5,325$2,358
RAG over documents
2,000 a day, 8K in, 600 out
$4,440$1,728
Coding agent
1,000 a day, 40K in, 2K out
$8,100$2,808
Overnight batch
20,000 a day, 4K in, 400 out
$33,600$7,200
Limits
Context window200K tokens1M tokens
Max output100K tokens128K tokens
Capabilities
Takes inImages, Text, PDFsText, 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
Always reasons
Built-in web search
Computer use
Fast mode
Native structured output