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
Released-28 Sep 2026
Status
Current
Current
Open weightsNoNo
Hosts
APIs you can call it on
48
Price · USD per million tokens, at the lab's own API where it sells the model
Priced atDeepInfraAnthropic
Input$2.00$2.00
Output$12.00$10.00
Cached input-$0.10
Batch
input / output
-$1.00 / $5.00
Cheapest anywhere
input / output
$2.00 / $12.00
DeepInfra
$2.00 / $10.00
Databricks
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
$1,500$1,179
RAG over documents
2,000 a day, 8K in, 600 out
$1,392$864
Coding agent
1,000 a day, 40K in, 2K out
$3,120$1,404
Overnight batch
20,000 a day, 4K in, 400 out
$7,680$3,600
Limits
Context window1M tokens1M tokens
Max output1M tokens128K tokens
Capabilities
Takes inText, Images, AudioText, 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
Native structured output