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
Released16 Nov 202621 Sep 202614 Aug 2026
Status
Current
Current
Current
Open weightsYes, Apache-2.0Yes, Apache-2.0Yes, Apache-2.0
Hosts
APIs you can call it on
2310
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atAlibaba DashScopeAlibaba DashScopeDeepInfra
Input$1.50$0.15$0.40
Output$4.50$0.47$3.00
Cached input$0.075$0.016$0.04
Batch
input / output
---
Cheapest anywhere
input / output
$1.43 / $4.28
Together AI
$0.15 / $0.47
Alibaba DashScope
$0.17 / $0.50
EmpirioLabs AI
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
$659$68.19$313
RAG over documents
2,000 a day, 8K in, 600 out
$540$56.76$214
Coding agent
1,000 a day, 40K in, 2K out
$873$95.64$358
Overnight batch
20,000 a day, 4K in, 400 out
$4,680$473$1,680
Limits
Context window992K tokens992K tokens262K tokens
Max output131K tokens131K tokens262K tokens
Capabilities
Takes inText, Images, VideoText, Images, Audio, VideoText, Images
ProducesTextTextText
Effort settings
as listed by the source
---
Streaming
Function calling
JSON mode
Structured outputs
Reasoning
Tool calling
Prompt caching
Built-in web search
Parallel tool calls